© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 10508
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal events and their descriptions

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

    detailed descriptions of violent incidents or criminal events with specific details about weapons, victims, and circumstances.

    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
    awakeFromNib
    -0.39
    slidesToShow
    -0.38
    Personensuche
    -0.38
    JsonValue
    -0.38
     kebersihan
    -0.36
    Bibliograf
    -0.36
    lapsingToolbar
    -0.35
    󠁣
    -0.35
    horabuena
    -0.35
     kasarigan
    -0.35
    POSITIVE LOGITS
     incident
    2.31
     incidents
    1.97
     Incident
    1.86
    incident
    1.81
     events
    1.79
    事件
    1.74
     incidente
    1.63
     kejadian
    1.60
     Incidents
    1.56
     peristiwa
    1.55
    Activations Density 1.030%

    No Known Activations