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. 21-GEMMASCOPE-RES-16K
    6. 15265
    Prev
    Next
    INDEX
    Explanations

    discussions or references to public financial systems and their impact on society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     co
    -0.85
     den
    -0.84
     par
    -0.82
     van
    -0.81
     da
    -0.81
     aux
    -0.80
     tr
    -0.78
     di
    -0.78
     ko
    -0.77
     ke
    -0.75
    POSITIVE LOGITS
     itſelf
    1.65
    The
    1.56
     Theſe
    1.43
     Jefus
    1.42
     Monfieur
    1.40
    There
    1.37
     Diſ
    1.34
     themſelves
    1.32
     myſelf
    1.31
     Reſ
    1.30
    Activations Density 1.108%

    No Known Activations