© 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. 11070
    Prev
    Next
    INDEX
    Explanations

    information related to motorcycle specifications and performance

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

    Tokens that appear with currency or prices

    np_acts-logits-general · gemini-2.0-flash

    India by

    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
    出版年
    -0.67
     ſta
    -0.65
     deſt
    -0.59
     myſelf
    -0.59
     ſch
    -0.57
     juſ
    -0.57
     saites
    -0.56
     plufieurs
    -0.55
     ſever
    -0.54
    Tikang
    -0.53
    POSITIVE LOGITS
     erst
    0.49
     India
    0.47
     buoyant
    0.42
    India
    0.42
    rawQuery
    0.40
     offering
    0.39
    Offering
    0.39
     Rajiv
    0.38
     india
    0.38
     offerings
    0.38
    Activations Density 0.066%

    No Known Activations