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. 7-GEMMASCOPE-RES-16K
    6. 2305
    Prev
    Next
    INDEX
    Explanations

    group-related elements and structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaikk
    -0.54
    bentar
    -0.51
     Polsek
    -0.50
     /
    -0.50
     كومونز
    -0.48
     amig
    -0.47
    /
    -0.47
    Източници
    -0.46
    честве
    -0.45
    øv
    -0.45
    POSITIVE LOGITS
    ]]
    
    0.79
    endphp
    0.75
     initComponents
    0.74
    __':
    
    0.74
     bezeichneter
    0.74
     CURIAM
    0.74
    .")]
    0.73
    __":
    
    0.73
    endpush
    0.72
    "]];
    0.72
    Activations Density 0.001%

    No Known Activations