© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 15924
    Prev
    Next
    INDEX
    Explanations

    references to heroes and associated themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dens
    -0.58
    ers
    -0.57
    pck
    -0.57
     informa
    -0.57
     Nü
    -0.56
    UNT
    -0.55
    Sanders
    -0.54
    kken
    -0.53
    Wander
    -0.52
    र
    -0.51
    POSITIVE LOGITS
     hero
    2.34
     Hero
    2.26
     HERO
    2.25
     heroes
    2.22
    hero
    2.18
    Hero
    2.07
    HERO
    2.03
     Heroes
    1.93
    heroes
    1.91
    Heroes
    1.79
    Activations Density 0.074%

    No Known Activations