© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104752
    Prev
    Next
    INDEX
    Explanations

    references to historical events and their impact on society

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

    Punctuation marks (commas, periods, question marks) and connecting words that appear at text breaks or transition points, often preceding quotation marks or line breaks, or marking pauses in written speech or song lyrics.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    دانشنامهٔ
    -0.47
    Cringe
    -0.42
    |}{}
    -0.42
     jspb
    -0.41
    StoryboardSegue
    -0.40
    NameInMap
    -0.40
     Walkover
    -0.40
    énario
    -0.39
     iParam
    -0.39
     ProtoMessage
    -0.37
    POSITIVE LOGITS
     rhyme
    0.45
     Chwiliwch
    0.44
    Autoritní
    0.43
     atracción
    0.41
     ***!
    0.40
    providedIn
    0.40
    +:+
    0.39
    ImageContext
    0.39
    hythm
    0.38
     noDo
    0.38
    Activations Density 0.134%

    No Known Activations