© 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. 5094
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting details within texts

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

    punctuation marks and special characters that separate clauses or sentences.

    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
     cliquant
    -0.39
    expandindo
    -0.35
     onClose
    -0.34
    cemment
    -0.34
     geholfen
    -0.33
    styleUrls
    -0.33
     updatedAt
    -0.32
    //
    -0.32
    centralwidget
    -0.32
     cambiando
    -0.31
    POSITIVE LOGITS
     make
    1.31
     take
    1.20
     Make
    1.11
     give
    1.09
    Make
    1.08
     try
    1.06
     put
    1.02
     keep
    1.02
     go
    1.01
     get
    1.01
    Activations Density 0.989%

    No Known Activations