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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 2227
    Prev
    Next
    INDEX
    Explanations

    evidence and references to material related to research and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.91
    parsedMessage
    -0.67
    jspx
    -0.65
    addGap
    -0.65
    uteurs
    -0.65
     Affiliations
    -0.65
    rieved
    -0.63
    WebVitals
    -0.62
    :+:
    -0.62
    arschijnlijk
    -0.62
    POSITIVE LOGITS
     stuff
    0.91
     footage
    0.87
    stuff
    0.84
    Stuff
    0.70
     imagery
    0.69
    rapnel
    0.68
     matériel
    0.66
     evidence
    0.66
     Stuff
    0.66
     STUFF
    0.65
    Activations Density 1.402%

    No Known Activations