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. 20-GEMMASCOPE-RES-131K
    6. 67368
    Prev
    Next
    INDEX
    Explanations

    terms related to movement and positioning in a gaming context

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

    pathogen release, fuel injected, move too

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jstor
    -0.45
    ereo
    -0.42
    Sampler
    -0.37
     نور
    -0.36
    Cliquez
    -0.36
     الدولى
    -0.35
     Ne
    -0.35
     voz
    -0.35
    niająca
    -0.35
    nor
    -0.35
    POSITIVE LOGITS
    TagMode
    0.51
     JpaRepository
    0.48
     GenerationType
    0.48
    ⤹
    0.45
    ึ้น
    0.45
    findpost
    0.43
    alyptus
    0.42
    CloseOperation
    0.41
    ToBounds
    0.41
     OMITBAD
    0.41
    Activations Density 0.171%

    No Known Activations