© 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. 31-GEMMASCOPE-RES-131K
    11. 64443
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to trial proceedings

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

    the state trial defendants jury

    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
    Bronnen
    -0.47
     paces
    -0.40
    rich
    -0.39
     little
    -0.38
    onAttach
    -0.37
     utafitiHapana
    -0.37
     hot
    -0.36
    Herzliche
    -0.36
     set
    -0.35
     nieuw
    -0.35
    POSITIVE LOGITS
     Court
    0.59
     cuestión
    0.57
     contextLoads
    0.57
     facts
    0.56
     spørs
    0.55
     questione
    0.55
    RegressionTest
    0.53
     вопрос
    0.52
     question
    0.52
    Court
    0.52
    Activations Density 0.556%

    No Known Activations