Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 3065
    Prev
    Next
    INDEX
    Explanations

    elements of scientific or mathematical notation and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    localctx
    -0.41
    afficheront
    -0.40
     &
    -0.34
     विश्वसनीयता
    -0.34
    EndProject
    -0.33
    躇
    -0.32
    OOTDTY
    -0.32
    MigrationBuilder
    -0.32
     canaux
    -0.31
    parsedMessage
    -0.31
    POSITIVE LOGITS
     للاسماء
    0.52
     linkovi
    0.49
    WriteBarrier
    0.48
    verwijspagina
    0.47
    nEnter
    0.46
     GoogleFonts
    0.45
    homonymie
    0.44
    EndContext
    0.44
     aluguel
    0.43
     NSCoder
    0.43
    Activations Density 0.297%

    No Known Activations