© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 3236
    Prev
    Next
    INDEX
    Explanations

    instances of reliance or agreements in statements

    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
    -1.20
    \{\\
    -1.07
    tagHelperRunner
    -1.01
    AndEndTag
    -0.99
     kasarigan
    -0.92
    parsedMessage
    -0.90
    enumii
    -0.90
     NUKAT
    -0.89
    StoryboardSegue
    -0.88
    OGND
    -0.88
    POSITIVE LOGITS
     upon
    2.86
    upon
    2.25
     UPON
    2.21
     Upon
    2.08
    Upon
    1.97
     apon
    1.27
     vpon
    1.08
     upo
    0.92
     asupra
    0.84
    pon
    0.78
    Activations Density 0.228%

    No Known Activations