© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 4188
    Prev
    Next
    INDEX
    Explanations

    legal terminologies and concepts related to criminal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unangemessene
    -0.39
     abuse
    -0.38
    談社
    -0.37
    المكان
    -0.36
     misconduct
    -0.35
     confis
    -0.35
     confiscated
    -0.34
     Abuse
    -0.33
     abusi
    -0.32
    RTSN
    -0.32
    POSITIVE LOGITS
     snippetHide
    0.67
     masked
    0.63
     armed
    0.63
     getaway
    0.58
     brazen
    0.56
     moti
    0.56
     motive
    0.55
     Masked
    0.54
    armed
    0.53
     perpé
    0.52
    Activations Density 0.773%

    No Known Activations