Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 6102
    Prev
    Next
    INDEX
    Explanations

    terms related to health metrics and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    blame
    -0.32
     suffer
    -0.29
     luta
    -0.28
     ķ
    -0.28
    Victim
    -0.28
    FFER
    -0.28
     wcześ
    -0.28
     vítimas
    -0.28
    ataires
    -0.28
    unknownFields
    -0.27
    POSITIVE LOGITS
     pinulongan
    0.63
    ThroughAttribute
    0.59
     ✭✭
    0.59
    Rüyada
    0.56
    phyla
    0.55
     GetEnumerator
    0.54
    eddable
    0.54
    enderror
    0.54
    vertible
    0.52
    ahalli
    0.52
    Activations Density 0.738%

    No Known Activations