© 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
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 5140
    Prev
    Next
    INDEX
    Explanations

    references to knives and stabbing incidents

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

    knives, blades and stabbing

    np_acts-logits-general · gemini-2.0-flash

    knives, blades, swords, daggers, stabbing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.69
    mobileqq
    -0.69
     estekak
    -0.65
    setVerticalGroup
    -0.59
    Portail
    -0.59
     Jefus
    -0.56
    Racer
    -0.56
    ſelves
    -0.56
     incrí
    -0.54
     itſelf
    -0.51
    POSITIVE LOGITS
     knife
    1.55
     knives
    1.41
     blade
    1.30
     Knife
    1.30
     blades
    1.18
    knife
    1.17
     Knives
    1.16
    Knife
    1.14
     pisau
    1.04
     Blade
    1.03
    Activations Density 0.270%

    No Known Activations