© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 11279
    Prev
    Next
    INDEX
    Explanations

    constructs related to GUI elements and event handling in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.43
    AppCompat
    -0.43
     oczeki
    -0.40
    ">//
    -0.39
    IsContent
    -0.38
     uſed
    -0.38
     nazy
    -0.38
     lenker
    -0.37
     Italij
    -0.36
    Rigidbody
    -0.36
    POSITIVE LOGITS
    ngrx
    0.57
    FormTagHelper
    0.55
    AndEndTag
    0.55
     nakalista
    0.55
     typelib
    0.51
    GraphicsUnit
    0.51
     estekak
    0.50
    EndGlobalSection
    0.48
    IUrlHelper
    0.47
    yarnpkg
    0.46
    Activations Density 0.199%

    No Known Activations