© 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. 20-GEMMASCOPE-RES-16K
    11. 15456
    Prev
    Next
    INDEX
    Explanations

    terms related to the destruction or defeat of characters and entities

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

    Something being defeated or destroyed

    np_acts-logits-general · gemini-2.0-flash

    is/being destroyed or defeated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.59
    phils
    -0.50
    Politics
    -0.49
    ési
    -0.48
    RunAsync
    -0.47
    ahren
    -0.47
    PageModule
    -0.46
     hyphen
    -0.45
     Alembic
    -0.45
    ynia
    -0.45
    POSITIVE LOGITS
     defeat
    0.98
     defeated
    0.94
     weaknesses
    0.79
     defeats
    0.79
    defe
    0.79
     neutralized
    0.79
     weakened
    0.78
     vanquished
    0.77
     Defeat
    0.76
     weaken
    0.74
    Activations Density 0.307%

    No Known Activations