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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5358
    Prev
    Next
    INDEX
    Explanations

    mentions of community involvement and concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    community members/residents

    np_acts-logits-general · gemini-2.0-flash

    community issues and residents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     globally
    -0.38
     worldwide
    -0.38
     global
    -0.34
    NACIONAL
    -0.33
     provinces
    -0.32
    global
    -0.30
     mundial
    -0.29
     îns
    -0.29
     świata
    -0.29
    Boxscore
    -0.29
    POSITIVE LOGITS
     residents
    1.14
     neighborhood
    1.10
    Residents
    1.08
     neighbors
    1.05
     Residents
    1.02
    residents
    1.02
     vecind
    0.95
     neighbourhood
    0.94
     vecinos
    0.94
     neighbours
    0.93
    Activations Density 0.348%

    No Known Activations