© 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-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8154
    Prev
    Next
    INDEX
    Explanations

    references to food items and dishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समीक्षाएं
    -0.44
    astify
    -0.42
    AutoScale
    -0.37
     ruban
    -0.36
    PreExecute
    -0.36
     espírito
    -0.36
    weightedMode
    -0.35
    ToFit
    -0.35
    Geplaatst
    -0.35
    SuppressLint
    -0.34
    POSITIVE LOGITS
     passive
    0.62
    Passive
    0.62
     Intellectual
    0.61
    passive
    0.61
     Passive
    0.60
    Unemployment
    0.60
     scaffolding
    0.59
    seamless
    0.59
    intellectual
    0.58
     intellectual
    0.58
    Activations Density 0.076%

    No Known Activations