© 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. 38-GEMMASCOPE-RES-16K
    11. 10449
    Prev
    Next
    INDEX
    Explanations

    restaurant reviews that highlight the quality and experience of the food and service

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

    punctuation marks that separate clauses, sentences, or list items.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.47
     review
    -0.44
    UserScript
    -0.41
    tonode
    -0.40
    ContentAsync
    -0.40
     damit
    -0.39
    epam
    -0.39
    Описание
    -0.38
    StoryboardSegue
    -0.38
    XmlEnum
    -0.38
    POSITIVE LOGITS
     Friendly
    0.86
     friendly
    0.85
    Friendly
    0.82
    friendly
    0.79
     nice
    0.65
    nice
    0.65
    plenty
    0.64
     lots
    0.63
     plenty
    0.63
    lots
    0.63
    Activations Density 0.066%

    No Known Activations