© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9599
    Prev
    Next
    INDEX
    Explanations

    references to numerical values and calculations within statements

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

    "What is the value of" questions

    np_acts-logits-general · gemini-2.0-flash

    value of

    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
    antMatchers
    -0.55
     transférez
    -0.55
    WebServlet
    -0.50
     JpaRepository
    -0.47
     CommonModule
    -0.45
    DropTable
    -0.45
     jsPsych
    -0.44
    utilisons
    -0.42
    RTLI
    -0.42
     оригіналу
    -0.42
    POSITIVE LOGITS
     value
    1.41
     values
    1.28
     Value
    1.26
     valeur
    1.25
     Values
    1.20
    value
    1.20
    Value
    1.15
     valeurs
    1.13
     VALUE
    1.13
     valore
    1.10
    Activations Density 0.636%

    No Known Activations