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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 7655
    Prev
    Next
    INDEX
    Explanations

    components of formal communication

    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
    LookAnd
    -0.54
     eorum
    -0.54
    来得
    -0.54
    ukone
    -0.53
    IsContent
    -0.52
    GRANTED
    -0.50
    BufferException
    -0.50
    Демографія
    -0.50
     ContentValues
    -0.50
     تضيفلها
    -0.49
    POSITIVE LOGITS
     Regards
    1.38
    Regards
    1.34
     regards
    1.33
    regards
    1.19
    Sincerely
    1.02
     regard
    0.99
     Sincerely
    0.98
    Cheers
    0.97
     Cheers
    0.96
    Best
    0.90
    Activations Density 0.391%

    No Known Activations