© 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. 11-GEMMASCOPE-RES-16K
    11. 14180
    Prev
    Next
    INDEX
    Explanations

    HTML/XML parameter names and attributes

    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
    SharedDtor
    -0.89
     '\\;'
    -0.89
    دانشنامهٔ
    -0.88
     tartalomajánló
    -0.86
    queryInterface
    -0.82
    Spoljašnje
    -0.82
     Италијани
    -0.82
     betweenstory
    -0.80
    setVerticalGroup
    -0.79
    featureID
    -0.79
    POSITIVE LOGITS
     rowspan
    0.83
     colspan
    0.74
     name
    0.69
    prepareStatement
    0.69
     cref
    0.67
     iParam
    0.65
    offsetof
    0.62
    LocalizedString
    0.60
     BoxDecoration
    0.60
    iParam
    0.59
    Activations Density 0.021%

    No Known Activations