© 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. 24-GEMMASCOPE-RES-16K
    6. 292
    Prev
    Next
    INDEX
    Explanations

    expressions or descriptors related to uniqueness and distinctiveness

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

    like "remarkable," "interesting," or "novel"

    np_acts-logits-general · gemini-2.0-flash

    introduces something remarkable or surprising

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cyfeiriadau
    -0.50
    IntoConstraints
    -0.45
     getContext
    -0.43
     båda
    -0.42
     Wikimedijinoj
    -0.40
     ardından
    -0.40
     Lingkungan
    -0.39
    beve
    -0.39
    ariConfig
    -0.38
     consommateurs
    -0.38
    POSITIVE LOGITS
     unusual
    0.77
     remarkable
    0.75
    unusual
    0.75
     strange
    0.72
     surprising
    0.70
     erstaun
    0.69
     astonishing
    0.69
    strange
    0.68
    Unusual
    0.68
     Unusual
    0.67
    Activations Density 0.225%

    No Known Activations