© 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. 31-GEMMASCOPE-RES-131K
    6. 24222
    Prev
    Next
    INDEX
    Explanations

    semicolon-separated values and HTML content type specifications

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

    ; followed by charset or boundary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.40
    LOYEES
    -0.35
    CLUD
    -0.34
     Seeder
    -0.34
    被打
    -0.33
    StatusOK
    -0.32
    chafter
    -0.32
    raborty
    -0.32
     repatri
    -0.32
     albicans
    -0.32
    POSITIVE LOGITS
     ब्रेकडाउन
    0.55
    
    0.54
     Numerade
    0.52
     nonUne
    0.52
     שוליים
    0.50
    GEBURTS
    0.50
    Cyfeiriadau
    0.50
    Rhestr
    0.50
    ConstraintMaker
    0.49
    salt
    0.47
    Activations Density 0.004%

    No Known Activations