© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 25055
    Prev
    Next
    INDEX
    Explanations

    references to software updates or application features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -1.23
    WriteBarrier
    -1.12
    Geplaatst
    -1.12
     صوتيه
    -1.09
    RectangleBorder
    -1.06
     lenker
    -1.05
    LookAnd
    -1.04
     <=",
    -1.04
    IndentedString
    -1.02
    GEBURTSDATUM
    -1.02
    POSITIVE LOGITS
     I
    0.48
     is
    0.46
     
    0.44
     They
    0.44
    I
    0.43
    .
    0.42
     made
    0.42
     on
    0.41
     so
    0.41
     for
    0.40
    Activations Density 0.024%

    No Known Activations