© 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. 9-GEMMASCOPE-RES-131K
    11. 76678
    Prev
    Next
    INDEX
    Explanations

    instances of the word "certain."

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

    certain

    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
    Grüsse
    -0.53
     Tasche
    -0.51
     hydropower
    -0.51
    wakili
    -0.50
     ideology
    -0.49
    zulegen
    -0.49
    ohyd
    -0.49
     Stool
    -0.49
     Grüsse
    -0.48
     Abenteuer
    -0.48
    POSITIVE LOGITS
     certain
    1.61
     Certain
    1.59
    Certain
    1.59
    certain
    1.51
     CERTAIN
    1.30
     certaine
    1.20
     ciertos
    1.16
     ciertas
    1.12
     bepaalde
    1.03
     tertentu
    1.00
    Activations Density 0.009%

    No Known Activations