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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 22457
    Prev
    Next
    INDEX
    Explanations

    numerical values, especially in the context of legal or procedural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abetes
    -0.83
    webElement
    -0.78
    цездатний
    -0.73
     Numerology
    -0.70
     mergeFrom
    -0.69
     EClass
    -0.68
    StructEnd
    -0.67
     getItemCount
    -0.67
    ulemon
    -0.67
    OGND
    -0.66
    POSITIVE LOGITS
    [toxicity=0]
    0.55
    <blockquote>
    0.50
    </h1>
    0.48
    *********/
    0.46
    .*")]
    0.45
    requently
    0.45
     »)
    0.44
    topes
    0.44
     виправивши
    0.44
    czywiście
    0.43
    Activations Density 0.032%

    No Known Activations