© 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. 20-GEMMASCOPE-RES-16K
    11. 256
    Prev
    Next
    INDEX
    Explanations

    references to goals and objectives

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

    "goal" and subsequent actions

    np_acts-logits-general · gemini-2.0-flash

    setting goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    는
    -0.71
    principalTable
    -0.65
    i
    -0.64
     विश्वसनीयता
    -0.63
    — 
    -0.63
    cleros
    -0.62
    ))){
    -0.60
    ところ
    -0.59
    EEEEEEEE
    -0.59
    ută
    -0.58
    POSITIVE LOGITS
    fillment
    0.66
    جستارهای
    0.60
    mobileqq
    0.59
    LLL
    0.58
    yakit
    0.58
     cala
    0.57
    IGraphics
    0.56
     Olms
    0.56
    orithmic
    0.55
    TextLabel
    0.55
    Activations Density 0.049%

    No Known Activations