© 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. 24-GEMMASCOPE-RES-16K
    11. 1215
    Prev
    Next
    INDEX
    Explanations

    special character sequences and symbols

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

    Non-English punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    after certain words

    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
     CreateTagHelper
    -0.81
     تضيفلها
    -0.79
     nahilalakip
    -0.75
    rungsseite
    -0.75
     surla
    -0.73
    ſchaft
    -0.73
    majánló
    -0.70
    ſicht
    -0.69
     كومونز
    -0.68
    SourceChecksum
    -0.68
    POSITIVE LOGITS
     tandis
    0.36
     sostuvo
    0.35
     lainnya
    0.33
     außerdem
    0.32
    ↵↵↵
    0.31
     ayrıca
    0.31
     asimismo
    0.30
     ardından
    0.30
     contactar
    0.30
     productividad
    0.30
    Activations Density 0.714%

    No Known Activations