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. 23-GEMMASCOPE-RES-16K
    6. 5836
    Prev
    Next
    INDEX
    Explanations

    names of actors and their roles in film and television productions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxDecoration
    -0.58
    Quentin
    -0.53
     nguyen
    -0.53
    PhysRevLett
    -0.51
     kasarigan
    -0.49
    begingroup
    -0.49
     Roskov
    -0.48
    Rè
    -0.48
     Limitation
    -0.47
     مواليد
    -0.47
    POSITIVE LOGITS
     ExecuteAsync
    0.74
    played
    0.68
     actores
    0.66
    Played
    0.61
    "]);
    
    0.58
     joué
    0.58
     actors
    0.58
    TemporalType
    0.58
     newcomer
    0.58
     Played
    0.57
    Activations Density 0.100%

    No Known Activations