© 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. 2547
    Prev
    Next
    INDEX
    Explanations

    statements of experience or opinion regarding personal feelings or perceptions

    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
    parsedMessage
    -0.48
    RegressionTest
    -0.47
    PreferredItem
    -0.47
     становника
    -0.44
     myſelf
    -0.42
    ंदीखरीदारी
    -0.41
     themſelves
    -0.39
     certes
    -0.38
    歟
    -0.37
     purpoſe
    -0.37
    POSITIVE LOGITS
     interesting
    0.67
     such
    0.66
     tricky
    0.61
     tough
    0.61
     huge
    0.60
     helpful
    0.59
     fascinating
    0.59
     phenomenal
    0.58
     important
    0.58
    huge
    0.57
    Activations Density 0.161%

    No Known Activations