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. 3-GEMMASCOPE-RES-16K
    6. 8375
    Prev
    Next
    INDEX
    Explanations

    sections or indicators in text denoting non-active content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portály
    -1.03
     himo
    -0.91
    ']))
    
    -0.90
    `,
    
    -0.85
    '],
    
    -0.82
    **/
    
    -0.81
     continúas
    -0.81
    ).</
    -0.81
    FieldNumber
    -0.79
    nologue
    -0.79
    POSITIVE LOGITS
    “
    0.71
    (
    0.69
     abiti
    0.66
    <strong>
    0.62
     الحره
    0.62
    <b>
    0.58
    "
    0.58
     pantaloni
    0.58
     felicità
    0.56
     provavelmente
    0.56
    Activations Density 0.032%

    No Known Activations