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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1188
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and elements related to programming and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by prepositions or parentheses

    np_acts-logits-general · gemini-2.0-flash

    plot, plt, scatter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.65
    LookAnd
    -0.49
     sumpay
    -0.48
    liceerd
    -0.46
    verifyException
    -0.44
     ویکی‌پدی
    -0.43
     autorytatywna
    -0.42
     RAP
    -0.41
     bes
    -0.41
    хьтан
    -0.41
    POSITIVE LOGITS
     instead
    0.53
    CloseOperation
    0.52
     leverage
    0.44
     sparingly
    0.42
     statt
    0.42
    ाहरण
    0.40
     istället
    0.39
     Mitteln
    0.38
     bantuan
    0.38
     anstatt
    0.37
    Activations Density 0.645%

    No Known Activations