© 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. 16-GEMMASCOPE-RES-16K
    11. 14639
    Prev
    Next
    INDEX
    Explanations

    discussions about interpersonal relationships and character dynamics

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

    appearing before actors' names

    np_acts-logits-general · gemini-2.0-flash

    actors starring in roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -0.66
    atimes
    -0.58
    ValueStyle
    -0.57
    itudinal
    -0.54
    Dorothy
    -0.54
    Abit
    -0.53
     дописавши
    -0.53
     conformité
    -0.53
    +#+#
    -0.52
     Sécurité
    -0.51
    POSITIVE LOGITS
     actors
    1.04
     actor
    1.01
     actores
    0.91
     Actors
    0.89
    Actors
    0.88
     actress
    0.88
     Actor
    0.81
     actresses
    0.79
     cast
    0.79
     star
    0.75
    Activations Density 0.188%

    No Known Activations