© 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
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 6787
    Prev
    Next
    INDEX
    Explanations

    instances of repeated conjunctions and phrases indicating multiple conditions or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LabelTagHelper
    -0.54
    quelles
    -0.53
     (†
    -0.46
    IndentedString
    -0.44
     bowiem
    -0.44
    (!)
    -0.44
     jedoch
    -0.44
    (
    -0.43
    first
    -0.42
     nämlich
    -0.42
    POSITIVE LOGITS
     then
    1.49
     it
    1.16
     whatnot
    1.14
     they
    1.13
     thats
    1.02
     there
    1.01
     voila
    0.97
     everything
    0.95
     thus
    0.94
     THEN
    0.94
    Activations Density 0.435%

    No Known Activations