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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2606
    Prev
    Next
    INDEX
    Explanations

    words related to technical specifications and dimensions

    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
    RenderAtEndOf
    -1.11
    AndEndTag
    -0.98
    richTextPanel
    -0.91
    Бахар
    -0.83
    PerformLayout
    -0.78
    GEBURTSDATUM
    -0.78
     архивлан
    -0.78
     שוליים
    -0.78
    verifyException
    -0.77
    SharedCtor
    -0.73
    POSITIVE LOGITS
    offset
    0.51
    Entire
    0.44
    roba
    0.43
    entire
    0.43
    1
    0.42
    gly
    0.41
    Δείτε
    0.38
     
    0.37
    USTIN
    0.36
    rob
    0.36
    Activations Density 0.051%

    No Known Activations