© 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. 17-GEMMASCOPE-RES-16K
    6. 9509
    Prev
    Next
    INDEX
    Explanations

    currency-related terms and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Schengen
    -0.62
     Shakspeare
    -0.60
     OTHERWISE
    -0.60
     Brahmin
    -0.57
     Euripides
    -0.56
    saurus
    -0.55
     Cæsar
    -0.54
    decin
    -0.54
     Molière
    -0.54
     AssemblyCulture
    -0.53
    POSITIVE LOGITS
     we
    1.19
     there
    1.13
     it
    1.04
     they
    0.93
     you
    0.85
    )";
    
    0.84
     this
    0.82
     the
    0.79
    )");
    
    0.78
    ")]
    
    0.76
    Activations Density 0.601%

    No Known Activations