© 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. 5-GEMMASCOPE-RES-16K
    11. 5491
    Prev
    Next
    INDEX
    Explanations

    occurrences of variable declarations in code

    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
    таратура
    -0.69
    protoimpl
    -0.69
     schie
    -0.65
    ByDefault
    -0.64
     сре
    -0.61
    ictwo
    -0.60
    enumi
    -0.60
    RegressionTest
    -0.59
    JpaRepository
    -0.59
     BitmapFactory
    -0.58
    POSITIVE LOGITS
    let
    2.02
    LET
    1.64
    lets
    1.48
    LETS
    1.19
     LET
    1.17
    Let
    1.07
     Let
    1.04
     let
    0.96
    лет
    0.90
    leti
    0.90
    Activations Density 0.100%

    No Known Activations