© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 16048
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters indicative of emotional expressions or questions

    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
     Himself
    -1.07
     Houſe
    -1.05
     Anſ
    -0.99
     Shakspeare
    -0.96
     Itself
    -0.90
     Jefus
    -0.89
     Eſ
    -0.89
     Efq
    -0.88
     himſelf
    -0.87
    ſelves
    -0.86
    POSITIVE LOGITS
     we
    1.35
     they
    1.32
     there
    1.27
     the
    1.24
     it
    1.20
     if
    1.20
     this
    1.13
     no
    1.11
     when
    1.11
     but
    1.08
    Activations Density 0.275%

    No Known Activations