© 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. 31-GEMMASCOPE-RES-131K
    6. 93229
    Prev
    Next
    INDEX
    Explanations

    references to wind and its characteristics

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

    wind blowing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Where Avali 2?

    No Comments

    Negative Logits
    ongiorno
    -0.45
     düşünü
    -0.44
     colgar
    -0.39
     humanidade
    -0.39
     Paglinawan
    -0.39
    ouvrage
    -0.39
     Berufung
    -0.38
    SizeMode
    -0.38
     Naciones
    -0.38
     pecho
    -0.37
    POSITIVE LOGITS
    enumii
    0.57
    CloseOperation
    0.57
     blowing
    0.55
    ScopeManager
    0.53
     privateKey
    0.53
     blow
    0.52
    findpost
    0.51
    FormTagHelper
    0.51
     blows
    0.51
    InputTagHelper
    0.50
    Activations Density 0.007%

    No Known Activations