© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 5271
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols within the text

    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
    Personendaten
    -0.90
     saites
    -0.89
    Билгалдахарш
    -0.85
    tagHelperRunner
    -0.82
    mybatisplus
    -0.79
    DebuggerNonUser
    -0.77
     विश्वसनीयता
    -0.75
     mergeFrom
    -0.73
    verwijspagina
    -0.71
     ffilmiau
    -0.71
    POSITIVE LOGITS
     Chwiliwch
    0.56
    Autoritní
    0.56
    ûte
    0.46
    brero
    0.45
     ')[
    0.44
    hasis
    0.42
    arakhand
    0.41
     Ramsey
    0.41
     Guaranteed
    0.40
     européen
    0.40
    Activations Density 0.330%

    No Known Activations