© 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. 6891
    Prev
    Next
    INDEX
    Explanations

    descriptions of weapons and violent actions

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

    referring to weapons

    np_acts-logits-general · gemini-2.0-flash

    weaponry and arms

    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
    zepine
    -0.53
    principalTable
    -0.53
    ValueGenerated
    -0.52
    ględ
    -0.50
     localVar
    -0.50
    cento
    -0.49
    oa̍t
    -0.47
    ]")]
    -0.45
     numerus
    -0.44
    jumper
    -0.44
    POSITIVE LOGITS
     weapon
    1.00
     weapons
    0.94
     Weapon
    0.79
     handheld
    0.79
    weapons
    0.78
     wielded
    0.76
    weapon
    0.76
     weaponry
    0.74
    Weapon
    0.68
     Weapons
    0.68
    Activations Density 0.298%

    No Known Activations