Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12801
    Prev
    Next
    INDEX
    Explanations

    terms related to superhero genres and associated box office success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.71
    <?
    -0.62
    rédients
    -0.59
    RenderAtEndOf
    -0.57
     naselje
    -0.56
    
    -0.55
    AnchorStyles
    -0.53
    odil
    -0.52
     démission
    -0.52
    Newswire
    -0.51
    POSITIVE LOGITS
     superheroes
    1.27
     Marvel
    1.25
     superhero
    1.23
    Marvel
    1.02
     Superhero
    1.02
     Batman
    1.00
     comic
    0.98
     Avengers
    0.98
     Disney
    0.98
     Superman
    0.94
    Activations Density 0.344%

    No Known Activations