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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 6195
    Prev
    Next
    INDEX
    Explanations

    terms related to biological functions and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olyb
    -0.55
     mapStateToProps
    -0.53
     Einkauf
    -0.52
     purchases
    -0.52
     purchase
    -0.51
     الاطلاع
    -0.51
    ształ
    -0.50
     compra
    -0.50
     reader
    -0.49
    rô
    -0.49
    POSITIVE LOGITS
     output
    1.08
     production
    0.96
     secretion
    0.94
    output
    0.90
     Output
    0.88
     emission
    0.86
     produced
    0.86
     producing
    0.84
    producing
    0.84
     release
    0.82
    Activations Density 0.860%

    No Known Activations