© 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. 28-GEMMASCOPE-RES-16K
    11. 5892
    Prev
    Next
    INDEX
    Explanations

    elements of code and mathematical expressions

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

    Negative numbers and related contexts

    np_acts-logits-general · gemini-2.0-flash

    negative numbers and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angerschaft
    -0.39
    TargetApi
    -0.31
    LabelTagHelper
    -0.31
    gigi
    -0.29
     Milestone
    -0.29
    TintMode
    -0.28
    práv
    -0.28
    keyColumn
    -0.28
    elaar
    -0.28
    visiae
    -0.28
    POSITIVE LOGITS
     negative
    1.73
     Negative
    1.50
    negative
    1.49
     NEGATIVE
    1.47
    Negative
    1.45
     negativo
    1.43
     negatives
    1.39
     négatif
    1.36
     negativity
    1.35
     negativos
    1.34
    Activations Density 2.531%

    No Known Activations