© 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. 7548
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific terminology and processes

    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
     toJson
    -0.47
    дра
    -0.44
    太平
    -0.42
    زل
    -0.39
    律
    -0.39
     Suprema
    -0.39
    심
    -0.39
     saluti
    -0.39
    Humph
    -0.38
    ERR
    -0.38
    POSITIVE LOGITS
     ***!
    1.00
     يتيمه
    0.96
    ніципалі
    0.90
    parsedMessage
    0.87
    RegistryLite
    0.80
     الدولى
    0.78
    mybatisplus
    0.77
     GenerationType
    0.76
    JspWriter
    0.75
    ⓧ
    0.75
    Activations Density 0.478%

    No Known Activations