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. 0-GEMMASCOPE-RES-16K
    6. 3441
    Prev
    Next
    INDEX
    Explanations

    references to specific pharmaceutical or chemical terms, particularly those related to various treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rele
    -0.60
     RequestMethod
    -0.58
    getDescriptor
    -0.56
    orithmic
    -0.54
    backslash
    -0.52
     HUM
    -0.51
     ses
    -0.51
     Jug
    -0.51
     Sta
    -0.51
     CORP
    -0.50
    POSITIVE LOGITS
    BE
    1.40
     PE
    1.36
    PE
    1.30
     CE
    1.29
    FE
    1.28
     TE
    1.28
    GE
    1.28
    TE
    1.27
    ZE
    1.27
    JE
    1.26
    Activations Density 0.147%

    No Known Activations