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. 20-GEMMASCOPE-RES-16K
    6. 12741
    Prev
    Next
    INDEX
    Explanations

    technical terms related to mathematical modeling and physics, specifically focusing on equations and parameters

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

    Parameters, constants, and coefficients in equations

    np_acts-logits-general · gemini-2.0-flash

    modelmodel parameters and coefficients

    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
     wireType
    -0.58
     concentric
    -0.47
     Bianchi
    -0.46
    ymce
    -0.45
     forState
    -0.41
    紋
    -0.41
    rodow
    -0.41
    dolu
    -0.41
    AppendLine
    -0.40
     presenti
    -0.40
    POSITIVE LOGITS
     parameters
    1.38
     coefficients
    1.27
     constants
    1.24
     parameter
    1.23
     Parameters
    1.21
     coefficient
    1.13
    parameters
    1.09
     paramètres
    1.06
     Coefficients
    1.05
     Parameter
    1.04
    Activations Density 1.592%

    No Known Activations