© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 681
    Prev
    Next
    INDEX
    Explanations

    phrases related to groups or collections of items, specifically in a scientific or statistical context

    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
    /
    -0.56
     and
    -0.56
    Many
    -0.49
    Certain
    -0.49
     certains
    -0.47
     or
    -0.47
     many
    -0.46
    Some
    -0.46
     galore
    -0.46
    many
    -0.45
    POSITIVE LOGITS
     queſta
    0.79
    各样的
    0.73
     interconnected
    0.71
     them
    0.69
     interrelated
    0.69
     oameni
    0.63
    قایناقلار
    0.62
     $_(
    0.61
     highly
    0.61
     different
    0.60
    Activations Density 0.402%

    No Known Activations