© 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. 31-GEMMASCOPE-RES-16K
    11. 14742
    Prev
    Next
    INDEX
    Explanations

    phrases indicating first-time occurrences or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases indicating something is being reported or done for the first time.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    كويكب
    -0.38
    rachtet
    -0.36
    asztal
    -0.35
    cửa
    -0.35
    ød
    -0.35
    tvguidetime
    -0.34
    asteroido
    -0.33
     Савезне
    -0.33
    Next
    -0.32
    Overlap
    -0.32
    POSITIVE LOGITS
     first
    1.91
     впервые
    1.79
     erstmals
    1.63
    初めて
    1.57
     pertama
    1.51
    第一次
    1.48
    first
    1.43
     första
    1.42
     første
    1.41
     popr
    1.40
    Activations Density 0.410%

    No Known Activations