© 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. 9-GEMMASCOPE-RES-131K
    6. 78066
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to cookies and responses in web applications

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

    code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.63
    دانشنامهٔ
    -0.55
     الحره
    -0.54
     незавершена
    -0.53
     كومونز
    -0.52
     Meksiku
    -0.52
    ParallelGroup
    -0.51
    Datuak
    -0.50
    Pyx
    -0.50
    AlterField
    -0.49
    POSITIVE LOGITS
    writel
    0.41
    setVerticalGroup
    0.40
     مرئيه
    0.37
    indd
    0.35
     död
    0.35
     sao
    0.34
    лосипе
    0.34
     setObject
    0.33
    EFIAPI
    0.33
    jsonwebtoken
    0.33
    Activations Density 0.293%

    No Known Activations