© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10483
    Prev
    Next
    INDEX
    Explanations

    references to networking or group structures in a technical context

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

    "group" or "groups"

    np_acts-logits-general · gemini-2.0-flash

    group identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Referències
    -0.35
     Italijanski
    -0.33
    lepiej
    -0.33
    სქოლიო
    -0.32
     calciatore
    -0.32
     FishBase
    -0.32
     חיצוניים
    -0.32
     ioutil
    -0.30
    énario
    -0.30
     eingeb
    -0.30
    POSITIVE LOGITS
     group
    1.76
    group
    1.75
     Group
    1.73
    Group
    1.72
     GROUP
    1.66
    GROUP
    1.59
     groups
    1.56
     Groups
    1.55
    groups
    1.50
    Groups
    1.45
    Activations Density 0.306%

    No Known Activations