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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16319
    Prev
    Next
    INDEX
    Explanations

    occurrences of URLs or web addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.55
    хьтан
    -0.52
    InSection
    -0.51
    DockStyle
    -0.49
     transférez
    -0.45
    Hochspringen
    -0.45
    Chham
    -0.45
     CiNii
    -0.44
    RunWith
    -0.43
    oa̍t
    -0.43
    POSITIVE LOGITS
    www
    0.62
     www
    0.59
    http
    0.43
     AssemblyCompany
    0.42
    issuer
    0.41
     ब्रेकडाउन
    0.40
     clin
    0.40
    Www
    0.40
    Portail
    0.39
     NTP
    0.39
    Activations Density 0.058%

    No Known Activations