© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 2037
    Prev
    Next
    INDEX
    Explanations

    terms related to populating and filling structures or datasets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    EXTR
    -0.54
    onStop
    -0.52
    Fin
    -0.51
     jazdy
    -0.50
     speciali
    -0.49
     EXTRACT
    -0.48
     Fin
    -0.48
     fin
    -0.47
    Année
    -0.47
    ρέπει
    -0.47
    POSITIVE LOGITS
     populated
    1.00
     populate
    0.97
     occupy
    0.92
     graced
    0.89
     occupying
    0.84
     resourceCulture
    0.83
    populated
    0.83
     inhabit
    0.83
     inhabited
    0.82
    featureID
    0.82
    Activations Density 0.545%

    No Known Activations