© 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. 4052
    Prev
    Next
    INDEX
    Explanations

    the presence of pro- prefix variations related to projects or proceedings

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

    words that begin with the prefix "Pro-" or "Pro".

    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
    alamat
    -0.31
    DIMENSION
    -0.28
    ale
    -0.28
    offsetHeight
    -0.28
     insert
    -0.27
     balas
    -0.27
     atmosf
    -0.27
     either
    -0.27
    attachments
    -0.26
     Mandel
    -0.26
    POSITIVE LOGITS
    Pro
    0.91
     Pro
    0.85
     pro
    0.84
    pro
    0.82
    Hochspringen
    0.70
    PRO
    0.69
    opro
    0.69
    pros
    0.69
    epro
    0.68
    procs
    0.68
    Activations Density 0.179%

    No Known Activations