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. 14127
    Prev
    Next
    INDEX
    Explanations

    references to polymer-related concepts and properties

    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
     оригіналу
    -0.86
    OGND
    -0.83
    BeginContext
    -0.83
    > 
    -0.82
     Etr
    -0.80
     Bessel
    -0.79
    קישורים
    -0.78
     pacman
    -0.77
    KURZBESCHREIBUNG
    -0.77
     Wot
    -0.76
    POSITIVE LOGITS
     POL
    0.90
     Pollack
    0.89
    mola
    0.83
     Pola
    0.82
     polskich
    0.80
     ALC
    0.77
    autore
    0.77
     politiques
    0.77
     poles
    0.77
     Desai
    0.77
    Activations Density 0.332%

    No Known Activations