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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 12181
    Prev
    Next
    INDEX
    Explanations

    references to databases and research publishing sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ))){
    -0.56
    ');?>
    -0.54
    }]
    
    -0.52
    ())))
    -0.48
     Studies
    -0.47
    DropColumn
    -0.46
     miss
    -0.46
    },{
    
    -0.45
    mbro
    -0.45
     fæ
    -0.45
    POSITIVE LOGITS
    참고
    0.80
     Administrativna
    0.76
    mbggenerated
    0.75
    enterOuterAlt
    0.71
     kasarigan
    0.69
     الرياضيه
    0.69
    ніципалі
    0.68
     SIMBAD
    0.68
     BytesLike
    0.68
     Argus
    0.66
    Activations Density 0.491%

    No Known Activations