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

    Neuronpedia

    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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 1573
    Prev
    Next
    INDEX
    Explanations

    phrases indicating financial impact or consequences

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

    the phrase "bottom line" as a concluding summary statement.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     ویکی‌پدی
    -0.50
    ServletException
    -0.42
     Comprometido
    -0.38
    zące
    -0.37
    ordonnées
    -0.37
     censiti
    -0.36
     continuidad
    -0.36
     Kindheit
    -0.35
     Hälfte
    -0.35
    ientôt
    -0.35
    POSITIVE LOGITS
     bottom
    2.27
     Bottom
    2.23
    Bottom
    2.05
    bottom
    1.80
     BOTTOM
    1.76
    BOTTOM
    1.67
     bottoms
    1.37
    底
    1.24
    botto
    1.14
     底
    1.05
    Activations Density 0.214%

    No Known Activations