© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 690
    Prev
    Next
    INDEX
    Explanations

    JavaScript DOM manipulation functions

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

    JavaScript DOM manipulation method calls

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

    DOM element access

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    !*\
    -0.71
    diğinde
    -0.63
    face
    -0.60
    '])->
    -0.60
    __':
    -0.60
    __':
    -0.58
     minY
    -0.58
    land
    -0.57
    liger
    -0.57
    Denny
    -0.57
    POSITIVE LOGITS
    getElementById
    0.98
    DidLoad
    0.59
    EDEFAULT
    0.58
    theid
    0.54
     AssemblyTitle
    0.53
     Juga
    0.53
    getElementsBy
    0.51
    freopen
    0.51
    myModal
    0.49
     Obrador
    0.49
    Activations Density 0.001%

    No Known Activations