© 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. 6525
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to data processes and operations

    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
     shui
    -0.44
    代替
    -0.42
     trasparente
    -0.42
     amélior
    -0.40
     revived
    -0.40
    ambito
    -0.39
     podjet
    -0.39
     acompañ
    -0.39
     vroe
    -0.39
    giques
    -0.38
    POSITIVE LOGITS
     يتيمه
    0.86
    Diweddarwch
    0.80
    Personensuche
    0.78
    ReusableCell
    0.77
    andExpect
    0.70
    </thead>
    0.69
    parsedMessage
    0.69
     CreateTagHelper
    0.69
     ContentValues
    0.66
     intStringLen
    0.65
    Activations Density 0.781%

    No Known Activations