© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8654
    Prev
    Next
    INDEX
    Explanations

    phrases related to arrest or apprehension in legal contexts

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

    arrests or being wanted

    np_acts-logits-general · gemini-2.0-flash

    wanted, arrested, charged

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnimationsModule
    -0.40
     rodzaju
    -0.35
    ंदीखरीदारी
    -0.35
    getActiveSheet
    -0.34
    ones
    -0.34
    voye
    -0.34
    Pragma
    -0.33
     formatos
    -0.33
    cine
    -0.32
     zug
    -0.32
    POSITIVE LOGITS
     arrested
    0.82
     arrest
    0.80
    Arrest
    0.74
     Arrest
    0.71
     arrests
    0.70
     tersangka
    0.67
     Arrested
    0.65
    arrest
    0.65
     indicted
    0.60
     suspect
    0.60
    Activations Density 0.511%

    No Known Activations