© 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-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 11812
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to pointers in programming languages, particularly C and C++

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
    kops
    -0.36
    الحياه
    -0.36
     chor
    -0.35
    ført
    -0.34
    teils
    -0.32
     manor
    -0.31
    vodní
    -0.31
    bonnet
    -0.31
     merci
    -0.31
     cár
    -0.30
    POSITIVE LOGITS
    URLException
    0.91
    WriteBarrier
    0.71
    XDECREF
    0.60
    EReference
    0.56
    findpost
    0.56
     مرئيه
    0.56
     GlobalKey
    0.55
    CPtr
    0.54
     '\\;'
    0.53
    UrlResolution
    0.52
    Activations Density 0.710%

    No Known Activations