Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1500
    Prev
    Next
    INDEX
    Explanations

    questions related to choices and comparisons

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

    Follows the word "of" and a question mark

    np_acts-logits-general · gemini-2.0-flash

    question marks and question phrases

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    OGND
    -0.76
     ब्रेकडाउन
    -0.64
    GTCX
    -0.62
     שוליים
    -0.57
    endpush
    -0.55
    ckså
    -0.55
     MainAxisSize
    -0.54
    StructEnd
    -0.53
    elemField
    -0.52
    IsMutable
    -0.52
    POSITIVE LOGITS
    ?
    0.89
    ؟
    0.72
    ?”
    0.72
    ?"
    0.71
    ?)
    0.71
    ?).
    0.70
    ?’
    0.69
    ?'
    0.65
    ?
    
    0.65
    ?",
    0.64
    Activations Density 0.529%

    No Known Activations