© 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. 3531
    Prev
    Next
    INDEX
    Explanations

    code elements related to menu and variable definitions

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

    Code, paths, and file-related strings

    np_acts-logits-general · gemini-2.0-flash

    `.getCssName(`

    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
     NSCoder
    -0.68
     فريبيس
    -0.58
     transférez
    -0.53
    們
    -0.50
    didReceive
    -0.45
    们
    -0.45
    HideFlags
    -0.45
     ब्रेकडाउन
    -0.45
    itespace
    -0.45
    queryInterface
    -0.45
    POSITIVE LOGITS
     //$
    0.72
     مشين
    0.71
     nameof
    0.69
    <bos>
    0.68
     <<<<<<<<<<<<<<
    0.68
    fromUtf
    0.67
    LookAnd
    0.67
    nameof
    0.67
    ]")]
    0.66
    SequentialGroup
    0.66
    Activations Density 0.428%

    No Known Activations