© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5844
    Prev
    Next
    INDEX
    Explanations

    elements related to photography sessions and the surrounding environment

    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
    ThroughAttribute
    -0.38
     provision
    -0.35
    AddWithValue
    -0.35
    umahan
    -0.35
     bygge
    -0.33
     שוליים
    -0.33
    MigrationBuilder
    -0.32
    InputTagHelper
    -0.32
     Seguridad
    -0.31
     Provision
    -0.31
    POSITIVE LOGITS
     photographing
    0.93
     photographer
    0.90
     photographers
    0.86
     photograph
    0.85
     photoshoot
    0.82
    photographer
    0.80
    photograph
    0.78
     photography
    0.77
     photographed
    0.75
     photographe
    0.75
    Activations Density 0.167%

    No Known Activations