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. 10379
    Prev
    Next
    INDEX
    Explanations

    references to telecommunications and technology components

    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
     bezeichneter
    -1.04
    =$?
    -1.03
    endsection
    -0.93
    }');
    -0.92
    __':
    
    -0.88
    <?>>
    -0.85
    __":
    
    -0.84
    endpush
    -0.83
    )');
    -0.82
    ViewInit
    -0.80
    POSITIVE LOGITS
    <blockquote>
    0.98
    </em>
    0.95
     [
    0.83
     …
    0.79
     vě
    0.76
    </blockquote>
    0.76
    …
    0.69
    <em>
    0.63
     Bisch
    0.63
                                   
    0.61
    Activations Density 0.014%

    No Known Activations