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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 23-GEMMASCOPE-RES-16K
    6. 12026
    Prev
    Next
    INDEX
    Explanations

    statistical terminology and concepts related to distributions and regression analysis

    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
     VIDEOTAPE
    -0.54
     SDLK
    -0.54
    Історія
    -0.54
     ExecuteAsync
    -0.54
    :✨
    -0.49
     ActionBar
    -0.49
    SPJ
    -0.49
    sonance
    -0.48
     Reactivity
    -0.47
     صوتيه
    -0.47
    POSITIVE LOGITS
     distribution
    0.98
     distributed
    0.95
     distributions
    0.85
     Distribution
    0.84
    distributed
    0.80
    Distribution
    0.80
     distribute
    0.79
     distributes
    0.79
    distribution
    0.78
     distribución
    0.78
    Activations Density 1.027%

    No Known Activations