© 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. 2240
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation in the text

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

    whitespace and numerical tokens in documents.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
     يتيمه
    -0.80
    tagHelperRunner
    -0.69
    XmlAccessType
    -0.67
     mxArray
    -0.65
    ſelf
    -0.65
     myſelf
    -0.64
     Reſ
    -0.62
     ſever
    -0.61
     AssemblyCompany
    -0.60
     faſt
    -0.60
    POSITIVE LOGITS
    <eos>
    0.38
    copg
    0.35
    ↵↵
    0.34
    ----------------
    0.34
     Италијани
    0.33
    gesch
    0.33
    ’
    0.32
    ↵
    0.32
     medi
    0.31
    fiant
    0.30
    Activations Density 0.137%

    No Known Activations