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. 24-GEMMASCOPE-RES-16K
    6. 949
    Prev
    Next
    INDEX
    Explanations

    terms related to education and academic structures

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

    Sections about structure, architecture, layout, and features

    np_acts-logits-general · gemini-2.0-flash

    campus club transport career poetry

    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
    webElementXpaths
    -0.61
    Chham
    -0.60
     nakalista
    -0.58
     utafitiHapana
    -0.56
     ſind
    -0.56
     laſſen
    -0.55
     Taktlose
    -0.53
     arada
    -0.52
     <>",
    -0.52
     CascadeType
    -0.51
    POSITIVE LOGITS
     structure
    0.37
     상세
    0.36
     layout
    0.34
     features
    0.33
     économiques
    0.33
    //~
    0.33
    特徴
    0.32
    förm
    0.32
    BASEPATH
    0.31
    ChildScrollView
    0.31
    Activations Density 0.229%

    No Known Activations