Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2034
    Prev
    Next
    INDEX
    Explanations

    specific technical or scientific terms related to data processing or modeling

    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
     OFDb
    -0.75
    Бахар
    -0.65
    :+:
    -0.64
    hyrchwyd
    -0.63
    Kariera
    -0.61
    WithIOException
    -0.61
    责任编辑
    -0.59
    ̈́
    -0.59
    ".
    
    -0.57
    sbury
    -0.57
    POSITIVE LOGITS
     onPostExecute
    0.67
     defaultstate
    0.54
    typeparam
    0.51
    ọa
    0.46
    initComponents
    0.44
     indisponible
    0.43
     skr
    0.43
    newArrayList
    0.42
     便
    0.42
     Whom
    0.42
    Activations Density 1.443%

    No Known Activations