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. 3-GEMMASCOPE-RES-16K
    6. 10094
    Prev
    Next
    INDEX
    Explanations

    numerical data, particularly associated with statistical metrics or measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bakgrunnsstoff
    -0.72
    DeleteBehavior
    -0.67
    IUrlHelper
    -0.62
    (&:
    -0.57
     QtCore
    -0.56
    omitempty
    -0.55
    (&_
    -0.54
    PerformLayout
    -0.54
     chi̍t
    -0.53
     копия
    -0.53
    POSITIVE LOGITS
     çık
    0.60
     Flin
    0.57
     Wedge
    0.55
     nakalista
    0.54
    wied
    0.54
    setFill
    0.54
    المناصب
    0.53
    ItemBackground
    0.52
    RegressionTest
    0.51
     planas
    0.51
    Activations Density 0.557%

    No Known Activations