© 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. 21-GEMMASCOPE-RES-16K
    6. 2745
    Prev
    Next
    INDEX
    Explanations

    structure and various properties related to object and value management in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.84
    SourceChecksum
    -0.73
     ModelExpression
    -0.69
    Diwedd
    -0.64
    Kjelder
    -0.63
     kaynağından
    -0.59
     CreateTagHelper
    -0.59
    »?
    -0.58
     насељу
    -0.58
    transQ
    -0.57
    POSITIVE LOGITS
    "
    
    0.82
    ");
    0.76
    ;");
    0.76
    ;
    0.72
    );
    0.68
    ")
    
    0.67
    '
    
    0.67
    "");
    0.66
    ");
    
    0.66
    ↵
    0.66
    Activations Density 0.110%

    No Known Activations