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. 4-GEMMASCOPE-RES-16K
    6. 11114
    Prev
    Next
    INDEX
    Explanations

    various forms of brackets or grouping symbols in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     viewType
    -0.57
     PPS
    -0.54
    ')")
    -0.53
    Gigi
    -0.52
     WIS
    -0.51
    (…)
    -0.51
    UnusedPrivate
    -0.50
    แผ
    -0.50
    Cursed
    -0.50
     qed
    -0.49
    POSITIVE LOGITS
    }{
    0.76
    addContainerGap
    0.71
    }{|
    0.70
    帖最后由
    0.70
    TagHelpers
    0.70
     localObject
    0.69
    httphttps
    0.68
     للاسماء
    0.67
    /*
    0.67
     HasFactory
    0.67
    Activations Density 0.083%

    No Known Activations