© 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-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 8393
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters commonly used in programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chartInstance
    -0.47
    PostInfinity
    -0.45
    glGen
    -0.45
    isas
    -0.42
    WriteTagHelper
    -0.40
    buro
    -0.38
    EndContext
    -0.38
    grà
    -0.36
     gale
    -0.36
    migrationBuilder
    -0.36
    POSITIVE LOGITS
     said
    0.88
     saying
    0.79
     says
    0.73
     berkata
    0.69
     mengatakan
    0.67
    他说
    0.66
     powiedzieć
    0.64
    saying
    0.63
     say
    0.63
    said
    0.63
    Activations Density 0.109%

    No Known Activations