© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 10627
    Prev
    Next
    INDEX
    Explanations

    significant statistical or mathematical indicators and results in various 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
    ので
    -0.76
    "],
    -0.75
     $[-
    -0.69
     Dresden
    -0.69
     seventies
    -0.69
    Hin
    -0.68
     Bourg
    -0.68
     pellic
    -0.67
    بوابة
    -0.66
     Basse
    -0.66
    POSITIVE LOGITS
    URLException
    0.99
     jLabel
    0.98
    httphttps
    0.91
    enumii
    0.85
    sidemargin
    0.79
    InSection
    0.78
    hasMoreElements
    0.77
    DIPSETTING
    0.76
    łada
    0.76
    ngths
    0.75
    Activations Density 0.429%

    No Known Activations