© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 8143
    Prev
    Next
    INDEX
    Explanations

    specific legal terms and conditions related to criminal cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.48
     Amp
    -0.37
     Tran
    -0.37
     Consultado
    -0.36
    <eos>
    -0.36
     principles
    -0.35
     Hend
    -0.35
     origin
    -0.35
    ".
    -0.35
     already
    -0.34
    POSITIVE LOGITS
     חיצוניים
    1.06
     שוליים
    0.77
     esterni
    0.71
     للاسماء
    0.65
     nahilalakip
    0.62
     Geſch
    0.59
    __*/
    0.59
    GEBURTS
    0.57
     kasarigan
    0.57
     Exacts
    0.56
    Activations Density 1.009%

    No Known Activations