© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 4605
    Prev
    Next
    INDEX
    Explanations

    statements about timing and urgency, particularly related to being too early or too late

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

    too early or too late

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cherchés
    -0.33
    EndInit
    -0.29
    inguém
    -0.28
     calzado
    -0.27
    ViewFeatures
    -0.26
     []:
    -0.24
    ิ่ง
    -0.23
    nowu
    -0.23
     vectorielle
    -0.23
    effetto
    -0.23
    POSITIVE LOGITS
     too
    1.60
    too
    1.44
     Too
    1.31
    Too
    1.31
     early
    1.20
     TOO
    1.20
    early
    1.17
     premature
    1.15
     late
    1.09
    Early
    1.06
    Activations Density 0.040%

    No Known Activations