© 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. 14543
    Prev
    Next
    INDEX
    Explanations

    snippets of code and programming syntax

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

    formatting elements and structural markers like dashes, brackets, and XML/code syntax delimiters.

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

    code and technical documentation, especially structured data formats like timestamps, file paths, and programming syntax.

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

    non-prose, highly structured technical text such as source code blocks, log/config records, and file/license headers with separators and timestamps

    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
    endpush
    -0.43
     motives
    -0.34
     ſta
    -0.34
    BagLayout
    -0.33
     bab
    -0.33
     abſ
    -0.32
     socie
    -0.32
     vacun
    -0.32
    Galería
    -0.31
     life
    -0.31
    POSITIVE LOGITS
     kasarigan
    0.78
    UrlResolution
    0.71
    
    0.66
    ikala
    0.64
     CanadaChoose
    0.61
    AndEndTag
    0.56
    Aholisi
    0.56
    ValueStyle
    0.56
    Personensuche
    0.52
    Географиясе
    0.52
    Activations Density 0.639%

    No Known Activations