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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 2363
    Prev
    Next
    INDEX
    Explanations

    key character names and their associated traits in a film context

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

    Tokens before/after actor names

    np_acts-logits-general · gemini-2.0-flash

    actors and their roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     kasarigan
    -0.79
    itudinal
    -0.72
     BoxDecoration
    -0.71
    getDescriptor
    -0.70
     Wikimedijinoj
    -0.68
    Gön
    -0.67
     CreateTagHelper
    -0.64
    InvalidProtocol
    -0.64
    ########.
    -0.64
    Geplaatst
    -0.63
    POSITIVE LOGITS
     actors
    1.20
     actor
    1.11
     actores
    1.09
     actress
    0.94
     Actors
    0.93
    played
    0.92
    Actors
    0.92
     cast
    0.88
     actresses
    0.86
     Actor
    0.85
    Activations Density 0.116%

    No Known Activations