© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 14797
    Prev
    Next
    INDEX
    Explanations

    programming-related expressions and operations involving string manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    R
    -0.48
    Interop
    -0.44
     hưởng
    -0.43
     differential
    -0.43
     invokingState
    -0.42
     Aff
    -0.42
    igree
    -0.41
     qualifications
    -0.41
    ग्री
    -0.41
     model
    -0.41
    POSITIVE LOGITS
     Replace
    0.79
    談社
    0.77
    tvguidetime
    0.76
    Replace
    0.76
     replace
    0.74
     replaces
    0.73
    replace
    0.73
    verwijspagina
    0.72
     Replacement
    0.70
    protoc
    0.68
    Activations Density 0.191%

    No Known Activations