© 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. 30-GEMMASCOPE-RES-16K
    11. 8328
    Prev
    Next
    INDEX
    Explanations

    references to limited edition items or offers

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

    "limited"

    np_acts-logits-general · gemini-2.0-flash

    limited offer or time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.59
    AndEndTag
    -0.56
    Portail
    -0.54
    BeforeMethod
    -0.48
    kömm
    -0.46
    OCCURRED
    -0.46
     Económica
    -0.43
    ChildIndex
    -0.43
    namiento
    -0.42
     età
    -0.42
    POSITIVE LOGITS
     limited
    1.92
    limited
    1.74
    Limited
    1.65
     Limited
    1.63
     LIMITED
    1.45
    LIMITED
    1.31
    限定
    1.25
     limitada
    1.13
     limitado
    1.12
     limitée
    1.11
    Activations Density 0.181%

    No Known Activations