© 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. 97468
    Prev
    Next
    INDEX
    Explanations

    references to directional changes in indicators, particularly upward and downward trends

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

    directional movement

    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
     głoś
    -0.32
     Avez
    -0.31
     szerző
    -0.31
    visející
    -0.30
     paille
    -0.29
     neutre
    -0.29
     prieten
    -0.29
     maș
    -0.29
     pingente
    -0.29
     burnt
    -0.28
    POSITIVE LOGITS
     downward
    1.02
     upward
    1.01
     downwards
    0.84
     upwards
    0.75
    脚注の使い方
    0.69
     estekak
    0.63
    向下
    0.63
     outward
    0.63
     northward
    0.62
    UnitTesting
    0.62
    Activations Density 0.029%

    No Known Activations