© 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. 9-GEMMASCOPE-RES-16K
    6. 8180
    Prev
    Next
    INDEX
    Explanations

    specific programming constructs and control structures, particularly loops and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.64
     Donaldson
    -0.63
     zufolge
    -0.52
    guardo
    -0.52
    ikala
    -0.51
    ept
    -0.51
    giant
    -0.50
    mazan
    -0.48
    HEP
    -0.48
     trebui
    -0.48
    POSITIVE LOGITS
    adpleegd
    0.84
     Vikipedi
    0.68
    </thead>
    0.60
    offsetof
    0.59
    __(/*!
    0.58
    SuppressLint
    0.55
    postIndex
    0.54
    Revenir
    0.53
     fieldNum
    0.53
     MemoryStream
    0.53
    Activations Density 0.176%

    No Known Activations