© 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. 24-GEMMASCOPE-RES-16K
    11. 6459
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to physical confrontations and violence

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

    Acts of physical violence

    np_acts-logits-general · gemini-2.0-flash

    physical assault and battery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     peč
    -0.53
     optimis
    -0.51
     percolation
    -0.50
    嘆
    -0.49
     quæ
    -0.47
     sécher
    -0.47
    alka
    -0.45
     installé
    -0.45
     rente
    -0.45
    DoesNotExist
    -0.45
    POSITIVE LOGITS
     punches
    1.33
     punched
    1.24
     punching
    1.22
     punch
    1.18
     assault
    1.15
     assaulting
    1.11
     assaulted
    1.10
     physically
    1.08
     beating
    1.08
     assaults
    1.04
    Activations Density 0.450%

    No Known Activations