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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1694
    Prev
    Next
    INDEX
    Explanations

    elements related to software development and technology terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     others
    -0.38
    expandindo
    -0.37
     esternos
    -0.36
    Manbalar
    -0.35
     differences
    -0.33
    قایناقلار
    -0.33
     other
    -0.31
     demás
    -0.31
     الأمريكية
    -0.31
     expectations
    -0.31
    POSITIVE LOGITS
    ⟬
    0.70
    ChildScrollView
    0.65
     للمعارف
    0.63
    principalColumn
    0.61
     パンチラ
    0.60
    FetchType
    0.59
    twimg
    0.59
    <unused80>
    0.57
    [@BOS@]
    0.57
    <unused8>
    0.57
    Activations Density 0.399%

    No Known Activations