© 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-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 4778
    Prev
    Next
    INDEX
    Explanations

    prominent words or phrases in various contexts, likely focusing on introductions or important statements

    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
    PreferredItem
    -1.26
    Personendaten
    -1.25
     незавершена
    -1.23
    AsUp
    -1.18
    EndContext
    -1.16
     الرياضيه
    -1.12
     "..\..\..\
    -1.10
     pinulongan
    -1.10
     AssemblyCulture
    -1.09
    MLLoader
    -1.08
    POSITIVE LOGITS
    ↵↵
    0.83
     
    0.79
    The
    0.69
     The
    0.69
    ↵
    0.66
     A
    0.63
    A
    0.60
    :
    0.58
    3
    0.57
    P
    0.57
    Activations Density 0.117%

    No Known Activations