© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 114954
    Prev
    Next
    INDEX
    Explanations

    terms and concepts associated with "impact."

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

    impact sprinkler, impact ionization, impact factory

    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
     mogelijkheden
    -0.52
     creazione
    -0.40
     speranza
    -0.39
     vertrouwen
    -0.39
     voordelen
    -0.38
     regels
    -0.38
     wensen
    -0.38
     Puedes
    -0.38
    enumi
    -0.37
     menyem
    -0.37
    POSITIVE LOGITS
    Impact
    1.37
     impact
    1.36
     Impact
    1.34
    impact
    1.34
     IMPACT
    1.28
    IMPACT
    1.20
     impacto
    1.09
     impacts
    0.99
     impac
    0.95
     Impacts
    0.94
    Activations Density 0.016%

    No Known Activations