© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 7900
    Prev
    Next
    INDEX
    Explanations

    numerical values and sequence representations

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

    Years

    np_acts-logits-general · gemini-2.0-flash

    years and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whether
    -0.48
     should
    -0.45
    should
    -0.44
    Should
    -0.42
     Should
    -0.38
     WHETHER
    -0.37
    whether
    -0.36
     shall
    -0.36
    是否
    -0.36
     do
    -0.34
    POSITIVE LOGITS
    Hentet
    0.82
     Administrativna
    0.81
    ########.
    0.68
    ,¹
    0.68
    ":[{
    0.66
    bootstrapcdn
    0.66
    сылкі
    0.65
    UrlResolution
    0.64
    .¹
    0.61
     للمعارف
    0.61
    Activations Density 1.077%

    No Known Activations