© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9379
    Prev
    Next
    INDEX
    Explanations

    template expressions and variable bindings in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DatabaseError
    -0.77
    Бахар
    -0.77
     sqlalchemy
    -0.77
     useState
    -0.73
     þat
    -0.71
    couvrez
    -0.71
     dataSnapshot
    -0.71
     prostu
    -0.71
     chemins
    -0.70
    useNewUrlParser
    -0.70
    POSITIVE LOGITS
    {{
    2.27
     {{
    1.77
     "{{
    1.48
     '{{
    1.46
     [[
    1.40
    [[
    1.34
    ="{{
    1.28
    [{{
    1.22
    ([[
    1.12
    ">{{
    1.09
    Activations Density 0.140%

    No Known Activations