© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8912
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal standards and evaluations of claims in court cases

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

    phrases indicating that something fails to meet a required threshold or standard (using the pattern "does/did not rise to the level of").

    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
    JMenu
    -0.29
    ceğini
    -0.27
    rimônio
    -0.25
    lagte
    -0.24
     panoramique
    -0.24
    обеди
    -0.24
    panjang
    -0.23
     meia
    -0.22
     Nuestros
    -0.22
     trasera
    -0.22
    POSITIVE LOGITS
     level
    2.75
     levels
    2.39
    level
    2.28
     niveau
    2.19
     Level
    2.17
     LEVEL
    2.17
    Level
    2.14
    levels
    2.03
     Levels
    2.03
     nivel
    2.03
    Activations Density 0.846%

    No Known Activations