© 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. 31-GEMMASCOPE-RES-16K
    11. 3034
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to liability and responsibility in various contexts

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

    expressions of legal liability and responsibility disclaimers.

    oai_token-act-pair · claude-4-5-haiku
    Triggered 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
    Negative Logits
     հղումներ
    -0.55
    antaranya
    -0.46
    usu
    -0.44
    lussen
    -0.44
    شو
    -0.43
    Eksterne
    -0.43
     PyTuple
    -0.43
     camped
    -0.43
    bando
    -0.43
     חיצוניים
    -0.42
    POSITIVE LOGITS
     responsibility
    2.03
     Responsibility
    1.74
    responsibility
    1.73
    Responsibility
    1.72
     accountability
    1.66
     responsabilité
    1.59
     responsabilidad
    1.55
     responsible
    1.53
     liability
    1.48
    責任
    1.48
    Activations Density 0.426%

    No Known Activations