© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 6820
    Prev
    Next
    INDEX
    Explanations

    references to violent actions, particularly shootings

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

    "shot" or "shoot"

    np_acts-logits-general · gemini-2.0-flash

    shooting people or things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Numerade
    -0.76
    theless
    -0.72
     metav
    -0.65
     hâte
    -0.63
     fermés
    -0.62
     Collapse
    -0.62
     Dacia
    -0.62
    defineProperty
    -0.61
    avro
    -0.60
    CodedInputStream
    -0.60
    POSITIVE LOGITS
     shots
    1.35
     shot
    1.29
     shoots
    1.22
     shooting
    1.21
    shots
    1.16
    shot
    1.16
     shoot
    1.15
    Shots
    1.11
     Shots
    1.10
     SHOT
    1.10
    Activations Density 0.217%

    No Known Activations