© 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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 125116
    Prev
    Next
    INDEX
    Explanations

    references to editorial positions, specifically emphasizing the role of "Editor-in-Chief."

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

    Editor-in-Chief or Chief Executive Officer

    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
    ExtendWith
    -0.54
     propOrder
    -0.50
    providedIn
    -0.49
    tvguidetime
    -0.46
     nakalista
    -0.45
    ⤒
    -0.44
    DRS
    -0.43
    kémon
    -0.43
    addCriterion
    -0.43
    TableAdapter
    -0.43
    POSITIVE LOGITS
    chief
    0.99
    Chief
    0.93
     Chief
    0.91
     CHIEF
    0.86
     chief
    0.81
    chiefs
    0.55
    IEF
    0.52
     CEO
    0.48
     Jefe
    0.47
    チーフ
    0.46
    Activations Density 0.003%

    No Known Activations