© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 46570
    Prev
    Next
    INDEX
    Explanations

    discussions related to hypotheses and their assumptions in research contexts

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

    used, ignoring, only, linear, data

    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
     Réponses
    -0.40
    NonNull
    -0.34
    endmodule
    -0.34
     gereken
    -0.33
     []).
    -0.32
    !("{}",
    -0.31
    ENCER
    -0.30
     Poy
    -0.30
    Sklici
    -0.30
    Klem
    -0.30
    POSITIVE LOGITS
     EconPapers
    0.59
     propOrder
    0.58
    Personendaten
    0.58
     ProtoMessage
    0.57
     HasFactory
    0.56
    TagMode
    0.55
     ivelany
    0.51
     Roskov
    0.50
    プローチ
    0.50
     AssemblyProduct
    0.49
    Activations Density 0.153%

    No Known Activations