© 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. 891
    Prev
    Next
    INDEX
    Explanations

    connections to scientific methodologies, data analysis, and population studies

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

    followed by commas

    np_acts-logits-general · gemini-2.0-flash

    medical samples and measurements

    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
    tagHelperRunner
    -0.66
    OGND
    -0.45
    MessageTagHelper
    -0.39
    fjspx
    -0.39
    GeoNames
    -0.39
    thâu
    -0.36
     ExecuteAsync
    -0.36
    delwed
    -0.35
    Kariera
    -0.34
    CardContent
    -0.34
    POSITIVE LOGITS
     often
    0.56
     itſelf
    0.53
     meanwhile
    0.53
     houſe
    0.52
     ſie
    0.52
     Inſ
    0.52
     therefore
    0.51
    wiſe
    0.51
     ſever
    0.50
     neceſſ
    0.50
    Activations Density 1.697%

    No Known Activations