© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 37-GEMMASCOPE-RES-16K
    11. 1138
    Prev
    Next
    INDEX
    Explanations

    various symbols and punctuation marks in the text, particularly periods and colons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.54
     houſe
    -0.46
    रीदारी
    -0.46
     themselves
    -0.44
     yourself
    -0.43
    šanās
    -0.43
     bouch
    -0.43
     moi
    -0.42
     ſte
    -0.41
    WhereInput
    -0.41
    POSITIVE LOGITS
    ']").
    0.46
    bri
    0.43
    evil
    0.42
     []:
    0.41
     schoenen
    0.41
    sha
    0.41
    הערות
    0.41
    ))->
    0.41
     liné
    0.40
    ped
    0.40
    Activations Density 0.181%

    No Known Activations