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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 23-GEMMASCOPE-RES-16K
    6. 10417
    Prev
    Next
    INDEX
    Explanations

    content related to rare automobiles and their specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doInBackground
    -0.59
    ukunfts
    -0.54
    IMPLEMENT
    -0.54
    Implement
    -0.52
     SqlDbType
    -0.52
     mapStateToProps
    -0.51
     mammalian
    -0.51
     ModelExpression
    -0.50
    stalline
    -0.50
    ayaquil
    -0.49
    POSITIVE LOGITS
     collectors
    1.08
     provenance
    0.99
     restoration
    0.98
     vintage
    0.98
     collector
    0.95
     Collectors
    0.92
    Collectors
    0.92
     restauration
    0.91
     restored
    0.91
    Restoration
    0.89
    Activations Density 0.186%

    No Known Activations