© 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. 6604
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or places within various contexts

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

    the word "place" and its surrounding context words like "where," "you," and "can."

    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
     незавершена
    -0.39
    toggler
    -0.39
     Participating
    -0.38
    Халык
    -0.35
    
    -0.34
    AntiForgeryToken
    -0.33
    Participating
    -0.33
    <bos>
    -0.31
    MessageOf
    -0.31
     Carried
    -0.30
    POSITIVE LOGITS
    SharedDtor
    0.69
     where
    0.69
     frequented
    0.65
    StoryboardSegue
    0.60
     visited
    0.59
    verifyException
    0.57
     où
    0.56
    visited
    0.55
     где
    0.55
    Autoritní
    0.55
    Activations Density 0.214%

    No Known Activations