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

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    11. 16367
    Prev
    Next
    INDEX
    Explanations

    lines of code or programming syntax

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

    Splitting strings or lines

    np_acts-logits-general · gemini-2.0-flash

    string splitting

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    活
    -0.44
    Cara
    -0.44
    +"'
    -0.44
     mortality
    -0.43
    piram
    -0.41
    yaszt
    -0.41
     Cara
    -0.40
    avimo
    -0.40
     baños
    -0.40
    󠁢
    -0.40
    POSITIVE LOGITS
     split
    1.33
     Split
    1.30
     StringTokenizer
    1.27
    StringTokenizer
    1.25
    split
    1.25
    Split
    1.21
     splitting
    1.12
     splits
    1.10
    sscanf
    1.09
    SPLIT
    1.03
    Activations Density 0.147%

    No Known Activations