© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28305
    Prev
    Next
    INDEX
    Explanations

    references to actions related to handling or managing containers or modules in code

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

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxxxx
    -0.55
    webElementXpaths
    -0.55
    Hochspringen
    -0.52
     joaat
    -0.51
    kháu
    -0.50
    ;"></
    -0.50
    inafter
    -0.50
    </thead>
    -0.49
    further
    -0.48
    
    -0.48
    POSITIVE LOGITS
    migrationBuilder
    0.60
    rungsseite
    0.59
    Javadoc
    0.55
    Submissions
    0.55
    tagHelperRunner
    0.54
    Dichloropropane
    0.53
    WebVitals
    0.52
    odyne
    0.51
    atur
    0.51
     Submissions
    0.50
    Activations Density 0.027%

    No Known Activations