© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13904
    Prev
    Next
    INDEX
    Explanations

    references to heroes and heroism in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     "
    -0.37
     ‘
    -0.36
     $\
    -0.36
     [
    -0.35
    gebracht
    -0.34
     \
    -0.34
     (
    -0.34
    s
    -0.34
     '
    -0.32
     Oeste
    -0.32
    POSITIVE LOGITS
    ValueStyle
    1.13
     HERO
    1.12
     Hero
    1.06
     hero
    1.06
    Hero
    1.05
    HERO
    1.01
    hero
    0.98
     heroes
    0.98
    Heroes
    0.95
     Heroes
    0.93
    Activations Density 0.104%

    No Known Activations