© 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. 28-GEMMASCOPE-RES-16K
    11. 10904
    Prev
    Next
    INDEX
    Explanations

    terms related to global scientific standards or classifications

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

    The token "Di" or "di"

    np_acts-logits-general · gemini-2.0-flash

    di- prefix words

    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
     autorytatywna
    -0.54
     Савезне
    -0.48
    RuleContext
    -0.47
     virtuel
    -0.46
    󠁬
    -0.45
     край
    -0.43
    fromnode
    -0.43
    UIControlState
    -0.43
    ModelAdmin
    -0.42
     espíritu
    -0.42
    POSITIVE LOGITS
     Di
    0.69
     di
    0.59
     DI
    0.57
    Di
    0.56
    MessageTagHelper
    0.49
     ComVisible
    0.48
    IConfiguration
    0.46
    InjectAttribute
    0.43
    Diver
    0.42
     Diver
    0.42
    Activations Density 0.182%

    No Known Activations