© 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. 90174
    Prev
    Next
    INDEX
    Explanations

    complex mathematical expressions and relationships involving variables in scientific contexts

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

    rate, difference, time

    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
    ſelves
    -0.57
    Попис
    -0.56
    ſelf
    -0.54
     Verſ
    -0.49
     Houſe
    -0.49
     houſe
    -0.48
     myſelf
    -0.45
    toFloat
    -0.45
    WithIOException
    -0.45
    цездатний
    -0.45
    POSITIVE LOGITS
    kać
    0.38
     Wiktionnaire
    0.38
     приходится
    0.35
     Ahnung
    0.35
     AssemblyTitle
    0.35
    Sprintf
    0.34
    TextFormField
    0.34
    
    0.34
    BooleanField
    0.33
    ?}",
    0.33
    Activations Density 0.306%

    No Known Activations