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. 15-GEMMASCOPE-RES-16K
    6. 5313
    Prev
    Next
    INDEX
    Explanations

    various numerical data and statistics related to performance and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſeveral
    -0.97
     Efq
    -0.93
     leaſt
    -0.91
    IntoConstraints
    -0.89
     myſelf
    -0.87
     purpoſe
    -0.87
     Theſe
    -0.85
    ſelf
    -0.85
     Conſ
    -0.84
     NSCoder
    -0.83
    POSITIVE LOGITS
     will
    1.15
     is
    1.11
     would
    1.05
     can
    1.05
     was
    1.03
     may
    1.01
     could
    0.96
     has
    0.93
     might
    0.90
     must
    0.89
    Activations Density 1.034%

    No Known Activations