© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 7688
    Prev
    Next
    INDEX
    Explanations

    references to heroic characters and themes of heroism in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "hero" or "heroes."

    np_acts-logits-general · gemini-2.0-flash

    hero, heroes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Demografia
    -0.60
    OGND
    -0.60
    EDEFAULT
    -0.59
    AddTagHelper
    -0.58
     dAtA
    -0.57
    XmlAccessType
    -0.57
    graffiti
    -0.56
     noDo
    -0.55
    cotch
    -0.55
    WriteTagHelper
    -0.54
    POSITIVE LOGITS
     Hero
    0.50
     HERO
    0.47
     hero
    0.44
    Hero
    0.41
    tagHelper
    0.40
    getName
    0.39
    hero
    0.38
    AccountId
    0.38
     Legend
    0.37
    appName
    0.36
    Activations Density 0.487%

    No Known Activations