© 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 - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 8758
    Prev
    Next
    INDEX
    Explanations

    terms related to listing and categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OBO
    -0.91
    +#+
    -0.86
     GenerationType
    -0.85
     "..\..\..\
    -0.85
    Искәрмәләр
    -0.84
    AJAS
    -0.82
     poffible
    -0.81
    CloseOperation
    -0.81
     juſt
    -0.81
     Hv
    -0.81
    POSITIVE LOGITS
     list
    1.36
     LIST
    1.32
    list
    1.24
     List
    1.23
    List
    1.11
     lists
    1.11
    LIST
    1.11
     Lists
    1.09
    lists
    1.02
    setList
    1.02
    Activations Density 0.076%

    No Known Activations