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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 587
    Prev
    Next
    INDEX
    Explanations

    references to collaborative committees and task forces in an economic or regulatory context

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

    committee and task force

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     palacio
    -0.38
    🩹
    -0.38
    ningss
    -0.38
    träd
    -0.38
    kedés
    -0.36
    kkende
    -0.36
    ậy
    -0.36
     olmayan
    -0.36
    TextUtils
    -0.35
     Quindi
    -0.35
    POSITIVE LOGITS
     committee
    0.90
    committee
    0.85
     Committee
    0.85
    Committee
    0.81
     COMMITTEE
    0.78
     subcommittee
    0.73
     Subcommittee
    0.73
     committees
    0.73
    tagHelperRunner
    0.72
     comité
    0.66
    Activations Density 0.097%

    No Known Activations