© 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-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 15603
    Prev
    Next
    INDEX
    Explanations

    structured notes or instructions that highlight specific tips, warnings, or updates

    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
     CreateTagHelper
    -1.04
    WebElementEntity
    -0.90
     Мексичка
    -0.88
    bootstrapcdn
    -0.85
    __(/*!
    -0.82
    ParallelGroup
    -0.82
     оригіналу
    -0.80
    AnchorStyles
    -0.80
    TagMode
    -0.77
    ScopeManager
    -0.77
    POSITIVE LOGITS
    :
    0.88
    :
    0.53
     :
    0.50
     that
    0.49
    ：
    0.44
    :#
    0.42
     note
    0.41
    Rè
    0.39
    .:
    0.37
     bahwa
    0.37
    Activations Density 0.308%

    No Known Activations