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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5632
    Prev
    Next
    INDEX
    Explanations

    statements about clinical evaluations and tests

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

    Following "not," "you," "I," or "is"

    np_acts-logits-general · gemini-2.0-flash

    expression of negation or doubt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.81
    
    -0.76
    berdayakan
    -0.70
     wikipagina
    -0.68
    MigrationBuilder
    -0.65
    </thead>
    -0.65
    uxxxx
    -0.63
    ThroughAttribute
    -0.61
     meats
    -0.60
    tvguidetime
    -0.60
    POSITIVE LOGITS
     („
    0.82
     „
    0.78
    ≙
    0.77
     hereby
    0.76
     ressources
    0.75
     therewith
    0.75
     (=
    0.74
     adresses
    0.74
     spez
    0.73
     startet
    0.73
    Activations Density 2.784%

    No Known Activations