© 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. 22-GEMMASCOPE-RES-16K
    11. 3113
    Prev
    Next
    INDEX
    Explanations

    references to violent acts and incidents

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

    shooting a firearm

    np_acts-logits-general · gemini-2.0-flash

    shooting and firing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apunov
    -0.60
     asyncio
    -0.58
     صوتيه
    -0.57
     فريبيس
    -0.55
     مرئيه
    -0.54
    acchar
    -0.54
    قایناق‌لار
    -0.53
    +#+#
    -0.53
    Composable
    -0.52
    racuse
    -0.51
    POSITIVE LOGITS
     shooting
    2.17
     shoot
    2.13
     shot
    2.08
     firing
    2.00
     shots
    1.90
     shoots
    1.85
     Shooting
    1.82
    shooting
    1.82
     Shoot
    1.81
     fired
    1.81
    Activations Density 0.377%

    No Known Activations