© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 31-GEMMASCOPE-RES-16K
    11. 15403
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings, specifically in the context of homicide and the justice system

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

    references to perpetrators of violent crimes, particularly words like "murderer," "killer," and "accused" in contexts describing criminal acts.

    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
    IVer
    -0.54
    цездатний
    -0.53
    JNIEnv
    -0.52
     ujednoznacz
    -0.51
    RefNanny
    -0.51
    屓
    -0.46
     Италијани
    -0.45
     cherchés
    -0.45
    govina
    -0.45
     NotImplemented
    -0.44
    POSITIVE LOGITS
     perpetrators
    1.45
     perpetrator
    1.40
     offender
    1.37
     offenders
    1.35
     culprits
    1.30
     criminals
    1.30
     suspects
    1.28
     culprit
    1.21
     murderer
    1.20
     murderers
    1.20
    Activations Density 0.668%

    No Known Activations