© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 12652
    Prev
    Next
    INDEX
    Explanations

    HTML header tags within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.54
    पया
    -0.52
    elemField
    -0.52
     channel
    -0.51
     typelib
    -0.50
     Channel
    -0.49
    apunov
    -0.48
    "';
    -0.46
    ';
    -0.46
    Channel
    -0.46
    POSITIVE LOGITS
    </h2>
    1.94
    ")]
    1.23
    ")]
    
    1.17
    */}
    1.01
    </s>
    1.00
    </h1>
    0.95
    </th>
    0.95
    <h2>
    0.89
    .")]
    0.77
     */}
    0.75
    Activations Density 0.013%

    No Known Activations