© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 4527
    Prev
    Next
    INDEX
    Explanations

    references to abuse, particularly in legal and discretionary contexts

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

    "abuse" or its variations

    np_acts-logits-general · gemini-2.0-flash

    abuse of discretion

    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
     surla
    -0.70
    
    -0.51
    HostException
    -0.48
    ษัท
    -0.47
    TALL
    -0.46
     Paglinawan
    -0.46
    ########.
    -0.46
     Tally
    -0.45
     Courant
    -0.44
    دانشنامهٔ
    -0.44
    POSITIVE LOGITS
     abuse
    1.91
    Abuse
    1.67
     Abuse
    1.65
    abuse
    1.62
     abused
    1.57
     abusing
    1.54
     abuses
    1.46
     abuso
    1.38
     abusive
    1.32
     abusos
    1.23
    Activations Density 0.203%

    No Known Activations