© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10303
    Prev
    Next
    INDEX
    Explanations

    reporting verbs that indicate speech or communication

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

    Attribution, direct quotes

    np_acts-logits-general · gemini-2.0-flash

    attribution verb

    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
     said
    -0.46
     was
    -0.45
    ScopeManager
    -0.38
     proble
    -0.35
    ized
    -0.35
     wasn
    -0.35
     had
    -0.35
     tersebut
    -0.34
    shutil
    -0.34
    ighted
    -0.34
    POSITIVE LOGITS
     says
    0.91
    Says
    0.90
    says
    0.83
     Says
    0.75
     SAYS
    0.74
    astify
    0.65
     říká
    0.64
     ExecuteAsync
    0.59
     می‌گوید
    0.58
     говорит
    0.53
    Activations Density 0.267%

    No Known Activations