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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9603
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and statistical notations.

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

    mathematical equations and formulas.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    mathematical subscript and superscript notation, particularly for indices and variables in equations.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot
    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
    IntoConstraints
    -0.72
     Inscrivez
    -0.57
     raiſ
    -0.53
     leſs
    -0.52
     ég
    -0.52
    ishly
    -0.51
     faſt
    -0.51
     eighty
    -0.50
     poffe
    -0.50
     ninety
    -0.50
    POSITIVE LOGITS
     AssemblyProduct
    0.59
    حوالہ
    0.59
    llium
    0.56
    QApplication
    0.56
    phazard
    0.56
     climá
    0.56
    genstein
    0.55
     HttpNotFound
    0.55
    rabbitmq
    0.54
    SuppressLint
    0.53
    Activations Density 0.538%

    No Known Activations