© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 1180
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to judicial proceedings

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Adjectives or adverbs before comparative "than"

    np_acts-logits-general · gemini-2.0-flash

    judging suitability or truthfulness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    renia
    -0.50
    idom
    -0.47
    bridi
    -0.46
    gameserver
    -0.46
    Portail
    -0.45
    theria
    -0.45
    fxml
    -0.44
    Jerusalem
    -0.44
    costal
    -0.44
    ussis
    -0.44
    POSITIVE LOGITS
     based
    0.49
     worth
    0.47
     according
    0.47
     EconPapers
    0.45
    NameInMap
    0.43
     AspNetCore
    0.40
    ContentAsync
    0.39
     BASED
    0.39
     jugement
    0.39
     dựa
    0.39
    Activations Density 0.814%

    No Known Activations