© 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. 38-GEMMASCOPE-RES-16K
    11. 13493
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to legal evidence and courtroom procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.46
    ureusement
    -0.44
     együtt
    -0.38
     Vordergrund
    -0.37
    舺
    -0.37
     przem
    -0.37
    ioma
    -0.36
    atiable
    -0.36
     '../../../../
    -0.36
    ivez
    -0.36
    POSITIVE LOGITS
     regarding
    3.02
    Regarding
    2.63
     Regarding
    2.61
    regarding
    2.61
     concerning
    2.52
     Concerning
    2.22
    Concerning
    2.20
     regards
    2.05
     concernant
    2.03
     respecto
    2.02
    Activations Density 2.132%

    No Known Activations