© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13408
    Prev
    Next
    INDEX
    Explanations

    references to locations or images related to specific content, particularly in a structured or formatted context

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

    dates and timestamps in various formats.

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

    low-quality, repetitive, or automatically generated web content and metadata.

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

    boilerplate metadata and templated web content, especially dates/timestamps, document headers, and SEO-style image gallery blurbs.

    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
    LookAnd
    -0.45
     spôso
    -0.44
     defaultstate
    -0.42
    NamedQueries
    -0.40
    StoryboardSegue
    -0.38
     Hentet
    -0.37
     fatiga
    -0.36
     Schließlich
    -0.36
     pauvreté
    -0.36
    InputBorder
    -0.36
    POSITIVE LOGITS
    +#+#
    0.77
    verwijspagina
    0.74
    Tikang
    0.72
    Diweddarwch
    0.67
    expandindo
    0.66
    WebElementEntity
    0.66
    Datuak
    0.63
    
    0.63
    tagHelperRunner
    0.60
    Rüyada
    0.58
    Activations Density 0.295%

    No Known Activations