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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 16376
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.67
     N
    -0.51
    袂
    -0.47
    фия
    -0.45
    AsUp
    -0.45
     areas
    -0.44
    nev
    -0.44
    TypedDataSet
    -0.44
    imba
    -0.44
    N
    -0.44
    POSITIVE LOGITS
    Equation
    0.85
    rungsseite
    0.83
    مصادر
    0.82
     Equation
    0.82
     equation
    0.81
    Eqn
    0.79
     '\\;'
    0.78
     nakalista
    0.75
    equation
    0.74
     eqn
    0.73
    Activations Density 0.548%

    No Known Activations