© 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-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 8004
    Prev
    Next
    INDEX
    Explanations

    names of locations or geographic entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Erkrankungen
    -0.40
     poète
    -0.37
     Fluss
    -0.37
     chileno
    -0.37
     Zudem
    -0.36
     adjunto
    -0.34
     maestra
    -0.34
     colombiana
    -0.34
     chilena
    -0.34
     Würde
    -0.33
    POSITIVE LOGITS
    migrationBuilder
    0.70
    mpagne
    0.69
    ロウィン
    0.63
    нгред
    0.61
    kuuta
    0.60
    iſchen
    0.59
    GHIJKLM
    0.58
     COT
    0.58
     zwiſchen
    0.58
    iſten
    0.57
    Activations Density 0.309%

    No Known Activations