© 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. 45518
    Prev
    Next
    INDEX
    Explanations

    adverbs and adjectives related to intentionality or purposeful actions

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

    acts done with intent

    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
     sidang
    -0.65
     ujednoznacz
    -0.63
     maș
    -0.57
     Inscrivez
    -0.55
    ulihan
    -0.55
     kennis
    -0.54
     argint
    -0.54
     küpe
    -0.53
    ppuden
    -0.53
    TagMode
    -0.53
    POSITIVE LOGITS
     deliberately
    1.81
     intentionally
    1.47
     deliberate
    1.39
     purposely
    1.36
     purposefully
    1.22
    故意
    1.13
     intentional
    1.11
     Deliber
    1.07
     sengaja
    0.97
    刻意
    0.97
    Activations Density 0.007%

    No Known Activations