© 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. 18-GEMMASCOPE-RES-16K
    11. 2494
    Prev
    Next
    INDEX
    Explanations

    discussions about diversity in superhero films

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

    Marvel's MCU and related characters/films

    np_acts-logits-general · gemini-2.0-flash

    Marvel Cinematic Universe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nargin
    -0.62
    celotti
    -0.57
    igslist
    -0.57
    NTIS
    -0.56
     Somaliland
    -0.56
     CDI
    -0.55
    TemporalType
    -0.55
     Bons
    -0.55
    ocracy
    -0.54
     MediatR
    -0.54
    POSITIVE LOGITS
     Marvel
    0.93
     MCU
    0.89
     Avengers
    0.80
    Marvel
    0.78
    Avengers
    0.77
     Spider
    0.75
     superhero
    0.74
    MCU
    0.69
    Spider
    0.62
    auri
    0.58
    Activations Density 0.160%

    No Known Activations