© 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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7129
    Prev
    Next
    INDEX
    Explanations

    data and parameters related to biochemical processes and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text or section headings

    np_acts-logits-general · gemini-2.0-flash

    scientific measurements and procedures

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    </strong>
    -0.59
    "?>
    -0.56
    "/>
    -0.55
    ֛
    -0.53
     】
    -0.53
    MENAFN
    -0.53
    </h1>
    -0.53
    </b>
    -0.52
    "}>
    -0.52
    POSITIVE LOGITS
    <h3>
    2.18
    </h2>
    1.02
    '),
    1.00
    ),"
    0.99
     */
    
    0.96
    </em>
    0.96
    </i>
    0.94
     \\
    0.94
     
    0.90
    </h3>
    0.89
    Activations Density 0.131%

    No Known Activations