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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 12339
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and constructs, particularly data type definitions and memory management functions

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

    Code and data structures

    np_acts-logits-general · gemini-2.0-flash

    data types and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.70
    ніципа
    -0.61
     endregion
    -0.60
    íncia
    -0.59
    ếng
    -0.54
    ceda
    -0.53
    bake
    -0.53
     degra
    -0.53
    θρω
    -0.52
    Билгалдахарш
    -0.51
    POSITIVE LOGITS
     ModelExpression
    0.68
    ScopeManager
    0.56
    帖最后由
    0.54
     OFDb
    0.53
    ReturnValue
    0.49
    Personendaten
    0.48
    ChildScrollView
    0.46
    原始内容存档于
    0.44
    cuerdo
    0.44
    族館
    0.43
    Activations Density 0.148%

    No Known Activations