© 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. 10-GEMMASCOPE-RES-16K
    6. 12194
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to user interface layout and design in coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DeleteBehavior
    -0.79
    apunov
    -0.77
    TargetException
    -0.71
    TagMode
    -0.61
    cshtml
    -0.60
     iprot
    -0.59
    はじめに
    -0.58
    ologico
    -0.58
     defaultstate
    -0.58
    VolleyError
    -0.57
    POSITIVE LOGITS
    menuStrip
    0.51
    habhar
    0.49
    Nguồn
    0.49
    ⓧ
    0.49
     extension
    0.49
    riezmann
    0.49
    malade
    0.48
     Reverso
    0.48
    umbersome
    0.47
    TagHelper
    0.47
    Activations Density 0.369%

    No Known Activations