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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 5626
    Prev
    Next
    INDEX
    Explanations

    layout parameters and settings for user interface components in Android

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    -1.47
     snippetHide
    -1.37
    AlterField
    -1.34
    tagHelperRunner
    -1.25
     EconPapers
    -1.21
    MemoryWarning
    -1.20
    setVerticalGroup
    -1.14
    tvguidetime
    -1.11
     الحره
    -1.11
     GenerationType
    -1.08
    POSITIVE LOGITS
    ↵↵
    0.55
     [
    0.52
    ,
    0.50
     ,
    0.48
     "
    0.47
    ...
    0.47
    -
    0.46
     and
    0.45
    [
    0.45
     (
    0.45
    Activations Density 0.016%

    No Known Activations