© 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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 13847
    Prev
    Next
    INDEX
    Explanations

    phrases and sections related to functions and parameters within programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.56
    mada
    -0.52
    ’
    -0.46
    .
    -0.45
    '
    -0.45
     all
    -0.44
     primary
    -0.44
     g
    -0.43
    <eos>
    -0.43
     N
    -0.43
    POSITIVE LOGITS
    IntoConstraints
    1.22
    makeConstraints
    1.13
    tvguidetime
    1.02
     whereabouts
    0.98
    BagConstraints
    0.98
     location
    0.98
    ConstraintMaker
    0.97
     getPosition
    0.96
    extAlignment
    0.96
    AnchorStyles
    0.92
    Activations Density 0.425%

    No Known Activations