© 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. 27-GEMMASCOPE-RES-16K
    11. 7575
    Prev
    Next
    INDEX
    Explanations

    non-verbal symbols and structural markers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vorlage
    -0.47
     مشين
    -0.43
    Pé
    -0.43
     chofe
    -0.40
    tvguidetime
    -0.40
     FAV
    -0.40
     argint
    -0.39
    Vorte
    -0.39
     gonzález
    -0.39
     vigil
    -0.39
    POSITIVE LOGITS
    ValueStyle
    0.55
     jadx
    0.51
    addCriterion
    0.50
     GenerationType
    0.49
     للمعارف
    0.47
     OFDb
    0.47
     esternos
    0.46
     незавершена
    0.45
     Catawiki
    0.44
    styleType
    0.42
    Activations Density 0.021%

    No Known Activations