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. 21-GEMMASCOPE-RES-16K
    6. 15081
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to measurements or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    setVerticalGroup
    -1.13
     AssemblyVersion
    -0.95
     ExecuteAsync
    -0.93
     Савезне
    -0.93
    +#+#
    -0.93
    хьтан
    -0.91
    rungsseite
    -0.91
    OGND
    -0.89
    Panamoan
    -0.88
    MigrationBuilder
    -0.88
    POSITIVE LOGITS
    {~
    0.76
    {
    0.60
    mathrm
    0.48
     ň
    0.47
     Rams
    0.46
     Turm
    0.46
    اسف
    0.45
    ıştır
    0.42
     있
    0.41
    clientWidth
    0.41
    Activations Density 0.018%

    No Known Activations