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. 15-GEMMASCOPE-RES-16K
    6. 12721
    Prev
    Next
    INDEX
    Explanations

    numerical data or structured information, particularly in a format involving various codes and categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.67
    setVerticalGroup
    -0.64
    ReusableCell
    -0.64
    principalTable
    -0.64
    ChildScrollView
    -0.61
     समीक्षाओं
    -0.59
     kyse
    -0.57
    følgelig
    -0.57
    .*")]
    -0.57
     jScrollPane
    -0.57
    POSITIVE LOGITS
    omitempty
    0.57
     juste
    0.57
     actionMode
    0.52
     continúas
    0.51
     block
    0.51
    COUVER
    0.50
    avana
    0.50
     vor
    0.50
     Juga
    0.49
     continuant
    0.49
    Activations Density 0.593%

    No Known Activations