Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 7761
    Prev
    Next
    INDEX
    Explanations

    terms related to numerical or mathematical representations and indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.74
     bunt
    -0.66
     prospectus
    -0.66
     CURIAM
    -0.65
     AssemblyCulture
    -0.63
     препратки
    -0.62
    Hauptartikel
    -0.61
    Personensuche
    -0.61
     Shakspeare
    -0.60
    MTL
    -0.60
    POSITIVE LOGITS
     increase
    1.05
     increased
    0.94
     increasing
    0.94
    dot
    0.88
     Increase
    0.87
     Increasing
    0.87
    Increase
    0.82
    increasing
    0.82
    increase
    0.81
    Increasing
    0.78
    Activations Density 0.145%

    No Known Activations