© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 7406
    Prev
    Next
    INDEX
    Explanations

    announcements and events

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

    announcements and event notices with dates and call-to-action information.

    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
     فريبيس
    -0.42
    intios
    -0.34
    PostExecute
    -0.34
     {}));
    -0.33
    exels
    -0.33
    bcryptjs
    -0.32
     biased
    -0.32
    FDRE
    -0.31
    基本的に
    -0.31
     sceptical
    -0.31
    POSITIVE LOGITS
    Upcoming
    1.01
    Reminder
    1.00
     upcoming
    0.94
     Upcoming
    0.92
     Announcement
    0.89
     Reminder
    0.88
    Congratulations
    0.88
     congratulations
    0.86
     announcement
    0.86
    Announcement
    0.84
    Activations Density 0.284%

    No Known Activations