© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 6513
    Prev
    Next
    INDEX
    Explanations

    references to software systems and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     juridiques
    -0.58
     publier
    -0.55
     travailleurs
    -0.54
     variés
    -0.53
     lecteurs
    -0.52
     financières
    -0.51
    retweeted
    -0.50
     cavity
    -0.50
     alér
    -0.50
     détru
    -0.50
    POSITIVE LOGITS
    Windows
    0.91
     Windows
    0.83
     windows
    0.60
    ComponentModel
    0.59
     CURIAM
    0.59
     يتيمه
    0.57
     المعيارى
    0.56
     DevComponents
    0.56
    Xaml
    0.56
    javax
    0.55
    Activations Density 0.009%

    No Known Activations