© 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. 31-GEMMASCOPE-RES-16K
    11. 16105
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings, investigations, and forensic analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical or formal language describing investigations, evidence, procedures, and official documentation.

    oai_token-act-pair · claude-4-5-haikuTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    AddHtmlAttribute
    -0.56
    ➯
    -0.55
    ⤹
    -0.47
    postsleuth
    -0.47
    encodeWith
    -0.46
    enumi
    -0.46
    ✢
    -0.45
    gradle
    -0.45
    Referanser
    -0.44
     endforeach
    -0.43
    POSITIVE LOGITS
     nakalista
    0.63
     &___
    0.58
     autorytatywna
    0.54
     Infórmanos
    0.51
     AUSSI
    0.50
     setempat
    0.49
     Njema
    0.48
     Italij
    0.48
    šanās
    0.47
     almofada
    0.47
    Activations Density 6.720%

    No Known Activations