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. 16379
    Prev
    Next
    INDEX
    Explanations

    contact-related communications and actions

    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
     zijne
    -0.46
     OMITBAD
    -0.44
     évêque
    -0.42
     figliu
    -0.38
    TestMethod
    -0.33
     chrétien
    -0.33
    новништво
    -0.32
     Sonnen
    -0.32
     ganchillo
    -0.32
    hoeddwyd
    -0.32
    POSITIVE LOGITS
     form
    1.16
     forms
    1.05
     Form
    1.00
     contact
    0.98
     Forms
    0.96
    contact
    0.95
    form
    0.94
    Form
    0.93
     Contact
    0.93
    forms
    0.91
    Activations Density 0.209%

    No Known Activations