© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 5453
    Prev
    Next
    INDEX
    Explanations

    numerical data related to measurements or quantities

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

    Numerical calculations or codes

    np_acts-logits-general · gemini-2.0-flash

    numbers, codes, and calculations

    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
    statechange
    -0.47
    ventud
    -0.43
     boya
    -0.42
     Privacidad
    -0.42
     OkHttpClient
    -0.41
     règne
    -0.40
    MockBean
    -0.40
    setCell
    -0.40
    HasForeignKey
    -0.39
    angerschaft
    -0.39
    POSITIVE LOGITS
    ariConfig
    0.47
    ApiModel
    0.44
     initComponents
    0.44
    HtmlAttribute
    0.43
     下午
    0.40
     Marlin
    0.40
    anyang
    0.39
    三百
    0.39
    ppio
    0.39
     Ause
    0.39
    Activations Density 1.581%

    No Known Activations