© 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. 15-GEMMASCOPE-RES-16K
    11. 12569
    Prev
    Next
    INDEX
    Explanations

    references to sharp objects and weapons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bullock
    -0.67
     bli
    -0.53
     Wre
    -0.51
     Volu
    -0.49
    nsyn
    -0.49
    MathML
    -0.48
     ballast
    -0.48
     hul
    -0.48
    coaster
    -0.48
    hup
    -0.46
    POSITIVE LOGITS
     knife
    1.34
     knives
    1.30
     sword
    1.20
     blades
    1.19
     blade
    1.17
     Knives
    1.16
     swords
    1.15
    Knife
    1.15
     Knife
    1.13
     Blades
    1.11
    Activations Density 0.392%

    No Known Activations