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. 21-GEMMASCOPE-RES-16K
    6. 6540
    Prev
    Next
    INDEX
    Explanations

    skills and experiences related to project management and production in a creative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.61
    endpush
    -0.45
    发表于
    -0.45
     nahilalakip
    -0.44
    Erreferentziak
    -0.43
     wrinkles
    -0.42
    rouvez
    -0.42
     Autorizaciones
    -0.41
     initComponents
    -0.41
    oplayer
    -0.41
    POSITIVE LOGITS
    contentLoaded
    0.46
     skills
    0.41
     compétences
    0.39
     Italijanski
    0.39
     Skills
    0.37
    💼
    0.36
     project
    0.36
     Pembangunan
    0.35
     projects
    0.35
    skills
    0.35
    Activations Density 0.141%

    No Known Activations