© 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. 43270
    Prev
    Next
    INDEX
    Explanations

    terms related to financial performance indicators, particularly changes in rates

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

    increase or higher values

    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
    .*")]
    -0.46
     intend
    -0.43
     Witness
    -0.43
     Kont
    -0.42
     endures
    -0.40
    ularis
    -0.40
    ритори
    -0.40
    glEnd
    -0.40
     intended
    -0.40
     Cont
    -0.39
    POSITIVE LOGITS
    increase
    0.81
     increase
    0.77
    Increase
    0.75
     hausse
    0.73
     zvý
    0.72
     kenaikan
    0.71
     INCREASE
    0.68
     HIGHER
    0.67
    higher
    0.66
     Increase
    0.66
    Activations Density 0.060%

    No Known Activations