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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8371
    Prev
    Next
    INDEX
    Explanations

    layout and UI configuration attributes alongside structured identifiers from software testing code fragments

    oai_token-act-pair · o3-miniTriggered by @yemengyus1

    technical terms related to programming and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -3.17
    ↵↵
    -0.87
    '
    -0.79
    ’
    -0.62
    ↵
    -0.48
     the
    -0.46
     itſelf
    -0.41
    The
    -0.40
    /*
    -0.40
    #
    -0.38
    POSITIVE LOGITS
    WEBPACK
    0.66
    󠁢
    0.63
    igshid
    0.62
    ertion
    0.61
     BrowserModule
    0.61
    AnchorStyles
    0.60
    ReusableCell
    0.60
     مشين
    0.60
    doctype
    0.59
    𓍊
    0.59
    Activations Density 6.334%

    No Known Activations