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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7150
    Prev
    Next
    INDEX
    Explanations

    instances of evidence or claims related to statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.67
    StoryboardSegue
    -0.59
     noDo
    -0.58
    VersionUID
    -0.56
    يميديا
    -0.52
    EndContext
    -0.52
    lccn
    -0.52
    EndGlobalSection
    -0.52
    awtextra
    -0.50
    ViewImports
    -0.49
    POSITIVE LOGITS
    ⎧
    0.45
     "*
    0.35
    Rohy
    0.34
     counter
    0.34
     
    0.33
    حياته
    0.32
     következő
    0.32
     Rad
    0.31
     tali
    0.31
    routeProvider
    0.31
    Activations Density 0.520%

    No Known Activations