© 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. 3260
    Prev
    Next
    INDEX
    Explanations

    technical terms related to communication protocols and electrical conductance

    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
    (!__
    -0.35
    MLLoader
    -0.35
     borda
    -0.32
    ibilità
    -0.30
    utex
    -0.30
     Carlo
    -0.29
    cesz
    -0.29
    MemoryWarning
    -0.28
    LOYE
    -0.28
     Widerspruch
    -0.28
    POSITIVE LOGITS
     channel
    3.80
     channels
    3.31
     Channel
    3.30
    channel
    3.23
    Channel
    3.13
     CHANNEL
    3.11
     Channels
    2.98
    CHANNEL
    2.75
    channels
    2.72
    Channels
    2.67
    Activations Density 0.907%

    No Known Activations