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. 38-GEMMASCOPE-RES-16K
    6. 10312
    Prev
    Next
    INDEX
    Explanations

    locations and geographical associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.61
     Nacionales
    -0.55
     Normdatei
    -0.52
     Seil
    -0.50
    mybatisplus
    -0.49
    Demografie
    -0.48
     Jerman
    -0.47
     Niedersachsen
    -0.46
    German
    -0.45
     Praga
    -0.45
    POSITIVE LOGITS
     Bad
    0.64
    Bad
    0.54
     bad
    0.52
    bad
    0.43
     Dink
    0.41
    BAD
    0.41
     Neck
    0.40
     Patt
    0.40
     BAD
    0.40
     Walden
    0.40
    Activations Density 0.474%

    No Known Activations