© 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. 3588
    Prev
    Next
    INDEX
    Explanations

    ellipses or visual breaks in text

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

    Text snippets containing technical information

    np_acts-logits-general · gemini-2.0-flash

    "raczej" non-English word

    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
    djangoproject
    -0.54
     menj
    -0.51
     scru
    -0.51
    pexpr
    -0.50
     (!__
    -0.50
    impresa
    -0.49
    AddTagHelper
    -0.49
     Benitez
    -0.49
    原神
    -0.49
    LabelTagHelper
    -0.48
    POSITIVE LOGITS
    ................
    0.69
    ."],
    0.58
     propOrder
    0.56
    BeginContext
    0.54
     snippetHide
    0.53
    ConstraintMaker
    0.53
    .';
    0.52
    ')")
    0.52
    .,"
    0.51
     raczej
    0.50
    Activations Density 0.117%

    No Known Activations