© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 5604
    Prev
    Next
    INDEX
    Explanations

    instances of numbers or numerical data

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

    Dates with day of the month "0[1-9]"

    np_acts-logits-general · gemini-2.0-flash

    dates and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    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
    -0.74
     Monfieur
    -0.71
     ſta
    -0.69
     houſe
    -0.69
     faſt
    -0.68
     pleaſure
    -0.68
     itſelf
    -0.67
     вікісторінку
    -0.65
     ſche
    -0.65
     Reſ
    -0.63
    POSITIVE LOGITS
    mathcal
    0.30
     earlier
    0.27
     M
    0.27
    ียง
    0.27
    mathbb
    0.26
     Lone
    0.25
     He
    0.25
    getElementsBy
    0.25
     The
    0.24
    Portale
    0.24
    Activations Density 0.528%

    No Known Activations