© 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. 35-GEMMASCOPE-RES-16K
    11. 12000
    Prev
    Next
    INDEX
    Explanations

    programming language syntax, particularly related to Integer and String data types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hdashline
    -0.41
    toMatchSnapshot
    -0.35
     school
    -0.35
    ättning
    -0.34
    AutoField
    -0.34
    nextDouble
    -0.33
     हुए
    -0.32
    ありますが
    -0.32
     illumination
    -0.32
     بهتر
    -0.30
    POSITIVE LOGITS
    DockStyle
    0.70
    ContentAsync
    0.64
    Havolalar
    0.63
    səhifə
    0.60
    BASEPATH
    0.57
    Personensuche
    0.56
    tvguidetime
    0.55
    Enllaces
    0.55
     nakalista
    0.55
    Kanpo
    0.54
    Activations Density 0.197%

    No Known Activations