© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 16913
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "there."

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

    there followed by being verbs

    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
    ly
    -0.44
    FontSize
    -0.43
    oauth
    -0.42
    Oste
    -0.40
    Golf
    -0.40
    userID
    -0.40
     Radio
    -0.39
    Vogue
    -0.38
    Polo
    -0.38
     Oste
    -0.38
    POSITIVE LOGITS
     there
    1.09
    there
    1.08
     THERE
    0.94
    There
    0.93
     There
    0.89
    THERE
    0.88
     חיצוניים
    0.66
     ब्रेकडाउन
    0.65
     theres
    0.65
    렷
    0.65
    Activations Density 0.074%

    No Known Activations