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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12133
    Prev
    Next
    INDEX
    Explanations

    references to teams and teamwork concepts

    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
    /**
    -0.51
    ullable
    -0.48
    URLException
    -0.46
     comércio
    -0.44
     agricultores
    -0.43
    Hauptartikel
    -0.40
     tượng
    -0.40
     cortas
    -0.39
    weilen
    -0.39
     zwarte
    -0.39
    POSITIVE LOGITS
    Team
    1.41
     Team
    1.32
     team
    1.29
    TEAM
    1.20
    team
    1.20
     TEAM
    1.19
    Teams
    1.10
     Teams
    1.09
     teams
    1.08
    getTeam
    1.08
    Activations Density 0.096%

    No Known Activations