© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 38485
    Prev
    Next
    INDEX
    Explanations

    references to object-oriented programming constructs, particularly the keywords "this" and "self"

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

    this or self followed by dot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    uxxxx
    -0.66
     незавершена
    -0.65
    CodedInputStream
    -0.61
     <>",
    -0.56
     estekak
    -0.54
    IntoConstraints
    -0.51
    ⓧ
    -0.51
    numerusform
    -0.50
    GeneratedCode
    -0.50
    styleType
    -0.50
    POSITIVE LOGITS
     createState
    0.46
     Kebijakan
    0.45
     Penga
    0.44
    Reserved
    0.43
    väg
    0.43
     picioare
    0.43
     chrétiens
    0.42
     Komunikasi
    0.40
    CODEC
    0.39
    ParallelGroup
    0.39
    Activations Density 0.003%

    No Known Activations