© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 734
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/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.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     мәкал
    -0.58
     resourceCulture
    -0.56
    rrggbb
    -0.55
     <<<<<<<<<<<<<<
    -0.54
     Италијани
    -0.53
    HtmlAttribute
    -0.52
    CloseOperation
    -0.52
     '\\;'
    -0.52
    BufferException
    -0.52
     Мексичка
    -0.51
    POSITIVE LOGITS
     super
    4.03
     Super
    3.92
    Super
    3.75
    super
    3.72
     SUPER
    3.36
    SUPER
    3.09
     супер
    2.94
    スーパー
    2.77
    Супер
    2.70
    超级
    2.66
    Activations Density 2.038%

    No Known Activations