© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3696
    Prev
    Next
    INDEX
    Explanations

    references to video content and media

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

    "video"

    np_acts-logits-general · gemini-2.0-flash

    video content or usage

    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
     dezelve
    -0.45
    Assemblée
    -0.44
     trouw
    -0.44
    iecie
    -0.44
     ilustraciones
    -0.43
     çat
    -0.42
     siècles
    -0.42
    essentiel
    -0.41
    approche
    -0.41
     gebied
    -0.40
    POSITIVE LOGITS
    Video
    0.96
     Video
    0.93
     video
    0.86
     Videos
    0.81
    video
    0.81
    存于互联网档案馆
    0.80
     VIDEO
    0.80
     videos
    0.76
    VIDEO
    0.71
    Videos
    0.71
    Activations Density 0.105%

    No Known Activations