© 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. 5515
    Prev
    Next
    INDEX
    Explanations

    statements that imply political affiliations or nominations

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

    and phrases that are being stated or said

    np_acts-logits-general · gemini-2.0-flash

    statement or phrasing

    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
     Houſe
    -0.56
    RTLI
    -0.53
     houſe
    -0.52
     myſelf
    -0.46
     informée
    -0.43
     itſelf
    -0.42
    GZIP
    -0.41
     Superhosts
    -0.41
     snippetHide
    -0.40
    Named
    -0.39
    POSITIVE LOGITS
     saying
    0.87
     phrase
    0.68
     statement
    0.64
     frasi
    0.62
     Saying
    0.62
     stating
    0.62
     dizendo
    0.62
    saying
    0.61
     diciendo
    0.60
    Saying
    0.60
    Activations Density 0.915%

    No Known Activations