© 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. 22-GEMMASCOPE-RES-16K
    11. 14597
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and verb forms indicating options or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nästa
    -0.31
     næste
    -0.31
     jöv
    -0.31
     Brücke
    -0.30
     próxima
    -0.28
     Spitze
    -0.26
     Deckel
    -0.26
    .
    -0.26
     próximos
    -0.25
     saksi
    -0.25
    POSITIVE LOGITS
    OGND
    0.77
    𑄮
    0.72
    <unused1>
    0.71
     メンテナ
    0.71
    <unused40>
    0.71
    <unused8>
    0.71
    <unused74>
    0.71
    <unused76>
    0.71
    <unused43>
    0.71
    <pad>
    0.71
    Activations Density 0.666%

    No Known Activations