© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 11565
    Prev
    Next
    INDEX
    Explanations

    repeated sequences or structures in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    large whitespace and formatting structures that organize tabular data.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    formatted tables and structured data layouts, particularly in legal and scientific documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    special formatting and layout markers—especially unusual whitespace/indentation—that signal tables, section breaks, lists, or math/technical formatting in structured documents.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.74
    contentLoaded
    -0.70
     nakalista
    -0.65
     חיצוניים
    -0.63
    Tikang
    -0.62
    webElementXpaths
    -0.59
    verwijspagina
    -0.59
     StatefulWidget
    -0.59
     CreateTagHelper
    -0.58
    WebElementEntity
    -0.57
    POSITIVE LOGITS
     ripar
    0.36
    募
    0.36
     share
    0.35
     downloading
    0.34
    сли
    0.34
     게
    0.34
     Loading
    0.33
     Empty
    0.33
     DOWNLOAD
    0.32
     Much
    0.32
    Activations Density 0.270%

    No Known Activations