© 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. 18-GEMMASCOPE-RES-16K
    11. 6823
    Prev
    Next
    INDEX
    Explanations

    actions related to decision-making and change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Verbs indicating completion or cessation of actions

    np_acts-logits-general · gemini-2.0-flash

    actions or changes of state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.84
     ModelExpression
    -0.76
     ་་
    -0.71
    contentLoaded
    -0.69
     raiſ
    -0.66
    MENAFN
    -0.63
     nakalista
    -0.63
     doubtnut
    -0.62
     للمعارف
    -0.61
    VIAF
    -0.61
    POSITIVE LOGITS
     the
    1.10
     from
    0.86
     without
    0.83
     as
    0.73
     with
    0.72
     a
    0.71
     throughout
    0.71
     for
    0.70
     beyond
    0.69
     in
    0.68
    Activations Density 0.576%

    No Known Activations