© 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. 22-GEMMASCOPE-RES-16K
    11. 8234
    Prev
    Next
    INDEX
    Explanations

    events related to sports and scoring actions

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

    Follows specific special characters or words

    np_acts-logits-general · gemini-2.0-flash

    Poly, script, reception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 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
     FetchType
    -0.61
    原始内容存档于
    -0.59
     neceff
    -0.55
    __["
    -0.53
    ┐
    -0.51
     pleaſure
    -0.51
     Austro
    -0.51
     insuffisamment
    -0.51
     abſ
    -0.50
    Hrsg
    -0.49
    POSITIVE LOGITS
     Moments
    0.67
    Moments
    0.65
     moments
    0.61
    ArgsConstructor
    0.60
    terase
    0.58
    ROIT
    0.56
    Parcelize
    0.55
     capped
    0.55
    PreferredItem
    0.55
     счет
    0.53
    Activations Density 0.109%

    No Known Activations