© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 76279
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "outcome."

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

    outcome or outcomes

    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
    fjspx
    -0.70
    깐
    -0.65
     preghi
    -0.59
     /*#__
    -0.58
     argint
    -0.57
    Carthy
    -0.56
    ſelf
    -0.55
     uffic
    -0.55
    ⓧ
    -0.55
    vertising
    -0.55
    POSITIVE LOGITS
     outcome
    1.33
     Outcome
    1.23
    Outcome
    1.23
    outcome
    1.20
     outcomes
    1.16
     Outcomes
    1.05
    Outcomes
    1.02
    outcomes
    1.01
     OUTCOMES
    0.84
     result
    0.71
    Activations Density 0.015%

    No Known Activations