© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 4619
    Prev
    Next
    INDEX
    Explanations

    algebraic or mathematical operations and terms

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

    structured numerical/math content, especially tabular statistics and equation-like expressions

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.75
    +#+#
    -0.64
    getWriter
    -0.59
    imageshack
    -0.58
    TagHelpers
    -0.57
    ledem
    -0.53
    ষ্
    -0.52
    laag
    -0.52
    ///</
    -0.52
    Étymologie
    -0.51
    POSITIVE LOGITS
     المعيارى
    0.61
    RenderAtEndOf
    0.58
    Примітки
    0.53
     مشين
    0.49
     فريبيس
    0.48
    Зноскі
    0.47
     estekak
    0.45
    CopyWith
    0.45
     intptr
    0.44
    ApiModelProperty
    0.44
    Activations Density 1.042%

    No Known Activations