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. 5416
    Prev
    Next
    INDEX
    Explanations

    statements that propose examples or scenarios for consideration

    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
     Efq
    -1.09
     EconPapers
    -1.08
    CloseOperation
    -1.04
     &___
    -1.01
     Monfieur
    -0.98
     ainfi
    -0.97
     myſelf
    -0.97
     ―――――
    -0.96
     raiſ
    -0.96
     purpoſe
    -0.95
    POSITIVE LOGITS
     example
    1.01
    Example
    0.85
    Imagine
    0.84
     Example
    0.82
     Imagine
    0.78
     examples
    0.75
    example
    0.75
     Suppose
    0.74
    举例
    0.71
     imagine
    0.71
    Activations Density 0.360%

    No Known Activations