© 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. 25-GEMMASCOPE-RES-16K
    11. 4854
    Prev
    Next
    INDEX
    Explanations

    terms related to product specifications and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.64
    mybatisplus
    -0.61
     дописавши
    -0.59
     TextInputType
    -0.52
     cellspacing
    -0.52
    "?>
    -0.51
    initializeApp
    -0.50
     bothering
    -0.49
     porté
    -0.49
    HomeAsUp
    -0.48
    POSITIVE LOGITS
     come
    0.94
    come
    0.74
     comes
    0.74
     work
    0.71
     feature
    0.68
     Come
    0.67
    Come
    0.66
     COME
    0.66
    comes
    0.60
     eignen
    0.58
    Activations Density 0.450%

    No Known Activations