Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13087
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and judicial processes

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

    Accusations, suspects, and arrests

    np_acts-logits-general · gemini-2.0-flash

    criminal accusations and charges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.60
    MigrationBuilder
    -0.59
    tagHelperRunner
    -0.55
    ukkig
    -0.53
     ModelExpression
    -0.52
     observer
    -0.51
     observers
    -0.50
    rrggbb
    -0.49
    cshtml
    -0.48
     converge
    -0.48
    POSITIVE LOGITS
     accused
    1.49
     suspects
    1.35
     convicted
    1.32
     suspect
    1.32
     suspected
    1.25
     arrested
    1.12
     indicted
    1.07
    accu
    1.01
     acusado
    1.01
     sospe
    0.94
    Activations Density 0.519%

    No Known Activations