© 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. 0-GEMMASCOPE-RES-16K
    6. 9222
    Prev
    Next
    INDEX
    Explanations

    applications and mentions of legal terms related to confessions and trials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.63
    ้งาน
    -0.52
     isolato
    -0.50
    addContainerGap
    -0.47
     supérieurs
    -0.46
     CreateTagHelper
    -0.46
    tvguidetime
    -0.46
     AssemblyCulture
    -0.46
    IContainer
    -0.46
     beroep
    -0.46
    POSITIVE LOGITS
     LO
    0.51
     hazards
    0.47
     Confession
    0.42
     confession
    0.42
     nas
    0.39
     hazardous
    0.39
    GEO
    0.38
     symmetric
    0.38
     članak
    0.37
     confess
    0.36
    Activations Density 1.599%

    No Known Activations