© 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. 9-GEMMASCOPE-RES-16K
    11. 9179
    Prev
    Next
    INDEX
    Explanations

    technical code elements, specifically related to addresses and data transfer

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

    code patterns related to "from" and "to" fields in programming structures.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disponibilità
    -0.34
     aapt
    -0.34
     drowned
    -0.31
    marshall
    -0.30
     SqlDbType
    -0.29
    PostInfinity
    -0.28
     bő
    -0.28
     intptr
    -0.28
     bare
    -0.28
    áját
    -0.27
    POSITIVE LOGITS
     SafeMath
    0.72
    TintMode
    0.68
    providedIn
    0.62
    parsedMessage
    0.59
    SafeMath
    0.59
     newOwner
    0.59
     betweenstory
    0.58
    ConverterFactory
    0.56
    execSQL
    0.54
    msgSender
    0.54
    Activations Density 0.082%

    No Known Activations