© 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. 83302
    Prev
    Next
    INDEX
    Explanations

    phrases indicating positive outcomes or potential in various contexts

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

    positive prospects and 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
    AddTagHelper
    -0.49
    momix
    -0.41
    rzez
    -0.38
     صوتيه
    -0.37
    chenkt
    -0.36
    ništ
    -0.35
     nettoyer
    -0.35
    FontOfSize
    -0.34
     jol
    -0.34
     Gesetze
    -0.33
    POSITIVE LOGITS
     prospects
    0.96
     hopeful
    0.93
     prospect
    0.82
     promising
    0.81
     Prospects
    0.78
     optimism
    0.73
     espoir
    0.73
     hope
    0.72
    hope
    0.68
     prognosis
    0.68
    Activations Density 0.028%

    No Known Activations