© 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. 3-GEMMASCOPE-RES-16K
    11. 8422
    Prev
    Next
    INDEX
    Explanations

    references to individuals involved in a homicide case

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.53
     Pickup
    -0.38
     pickup
    -0.38
    拾
    -0.37
     train
    -0.37
     mango
    -0.37
     Langer
    -0.37
     Pino
    -0.36
     versus
    -0.36
    detached
    -0.35
    POSITIVE LOGITS
    tagHelperRunner
    0.71
     HENRY
    0.70
    Henry
    0.70
     Henry
    0.69
    ani
    0.68
     honey
    0.68
    +#+#
    0.64
    henry
    0.62
     HONEY
    0.61
    NameInMap
    0.60
    Activations Density 1.172%

    No Known Activations