© 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. 18-GEMMASCOPE-RES-16K
    11. 3962
    Prev
    Next
    INDEX
    Explanations

    events involving firearms and related violence

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

    guns and shooting

    np_acts-logits-general · gemini-2.0-flash

    firing or shooting

    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
     Picchu
    -0.63
     صوتيه
    -0.57
    +#+#
    -0.57
     referenties
    -0.55
    ulemon
    -0.50
     NACA
    -0.50
     annuelle
    -0.48
    RTDA
    -0.47
    piac
    -0.47
     Druid
    -0.47
    POSITIVE LOGITS
     shooting
    1.66
     shoot
    1.51
     Shooting
    1.51
    shooting
    1.44
     shot
    1.43
     Shoot
    1.40
     gun
    1.40
     bullets
    1.39
    Shooting
    1.39
     shots
    1.38
    Activations Density 0.226%

    No Known Activations