© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9993
    Prev
    Next
    INDEX
    Explanations

    references to acts of killing or murder

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

    "kill" and its variations

    np_acts-logits-general · gemini-2.0-flash

    ending or destroying

    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
    Mateo
    -0.50
     Administrativna
    -0.49
    ContextCompat
    -0.48
     lateinit
    -0.48
     Stefan
    -0.48
     WPF
    -0.47
     Seaside
    -0.47
     Mateo
    -0.46
    Stefan
    -0.46
     Requests
    -0.46
    POSITIVE LOGITS
     kill
    1.77
     killing
    1.65
     kills
    1.60
     Kill
    1.59
    Kill
    1.59
     KILL
    1.55
     killed
    1.54
    kill
    1.53
    killing
    1.49
     Killing
    1.47
    Activations Density 0.169%

    No Known Activations