© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15806
    Prev
    Next
    INDEX
    Explanations

    keywords related to murder, execution, and criminal activities

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

    murder, killing, homicide

    np_acts-logits-general · gemini-2.0-flash

    brutal murder or killings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.59
    ukone
    -0.57
    hips
    -0.54
    MLLoader
    -0.54
    TagMode
    -0.54
    GEBURTSDATUM
    -0.51
     nén
    -0.51
    RTEX
    -0.51
    ariConfig
    -0.50
    oneofs
    -0.49
    POSITIVE LOGITS
     murder
    1.26
     murders
    1.13
     killings
    1.08
     killing
    1.04
     homicide
    1.02
     killers
    0.98
    murder
    0.97
     homic
    0.94
     murdered
    0.93
     murdering
    0.92
    Activations Density 0.588%

    No Known Activations