© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 114638
    Prev
    Next
    INDEX
    Explanations

    the adverb "definitely" and its variations, indicating a strong affirmation or certainty

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

    definitely + descriptor

    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
     HasFactory
    -0.58
    RenderAtEndOf
    -0.58
     JpaRepository
    -0.53
     resourceCulture
    -0.52
     ſch
    -0.52
     unknownFields
    -0.52
    protoimpl
    -0.51
    InstrumentedTest
    -0.50
     armées
    -0.50
     ſol
    -0.49
    POSITIVE LOGITS
     Definitely
    1.27
     definitely
    1.27
    Definitely
    1.24
    definitely
    1.22
     definately
    1.09
     certainly
    0.95
     definite
    0.84
     definitivamente
    0.83
    certainly
    0.82
     DEFIN
    0.81
    Activations Density 0.009%

    No Known Activations