© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8709
    Prev
    Next
    INDEX
    Explanations

    terms related to participation and involvement in initiatives or programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betrek
    -0.53
    zijde
    -0.47
    blå
    -0.46
     zijne
    -0.45
     auroit
    -0.44
     beschik
    -0.44
     wikipagina
    -0.43
     fédé
    -0.43
     protoimpl
    -0.43
    gæ
    -0.43
    POSITIVE LOGITS
    engagement
    1.15
    ishment
    1.15
    Attachment
    1.13
    AGEMENT
    1.11
     engagement
    1.10
     Enhancement
    1.09
    agement
    1.09
     Attachment
    1.08
     Engagement
    1.08
    tainment
    1.08
    Activations Density 0.162%

    No Known Activations