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

    Neuronpedia

    Jacobian LensNEW
    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. 21276
    Prev
    Next
    INDEX
    Explanations

    instances of the word "obvious" and related phrases or adjectives indicating something is clear or evident

    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
    principalColumn
    -0.80
    uberge
    -0.79
    templateUrl
    -0.69
     efectivamente
    -0.69
    nestjs
    -0.68
    frameCount
    -0.68
    RepeatedField
    -0.68
     efficacement
    -0.68
    protoimpl
    -0.66
    itudine
    -0.66
    POSITIVE LOGITS
    VIOUS
    1.09
    ness
    0.97
     obvious
    0.84
    Obvious
    0.82
    obvious
    0.80
     Justo
    0.80
    $
    
    0.78
    ']))
    
    0.77
    */;
    0.77
    "];
    
    0.77
    Activations Density 0.021%

    No Known Activations