© 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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105597
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax related to function calls and object manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     profumo
    -0.41
     establishment
    -0.40
    transQ
    -0.40
     ESTABL
    -0.39
     Establishment
    -0.39
    Establishment
    -0.38
     Duft
    -0.38
    berdayakan
    -0.37
    クタイ
    -0.37
    stdarg
    -0.36
    POSITIVE LOGITS
     kasarigan
    0.67
    migrationBuilder
    0.54
    SharedDtor
    0.52
    SharedCtor
    0.50
     CreateTagHelper
    0.50
     виправивши
    0.49
    InitVars
    0.48
    出版年
    0.48
    thâu
    0.46
    izr
    0.45
    Activations Density 0.013%

    No Known Activations