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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 6732
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific findings and observations in a medical or biological context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    ؛
    -0.59
     correctes
    -0.59
     NSCoder
    -0.56
    rawDesc
    -0.54
     DbType
    -0.54
    .
    -0.54
    ;
    -0.51
    CompleteListener
    -0.51
     незавершена
    -0.51
    getMenuInflater
    -0.50
    POSITIVE LOGITS
    }$.\\
    1.60
    ).\\
    1.47
    <eos>
    1.44
    $.\\
    1.39
    ).}
    1.17
    ."""
    1.17
    </tbody>
    1.16
    ).
    
    1.13
    }.
    
    1.12
    .\\
    1.11
    Activations Density 1.784%

    No Known Activations