© 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. 3-GEMMASCOPE-RES-16K
    11. 8843
    Prev
    Next
    INDEX
    Explanations

    quantitative information related to measurements and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -0.83
     or
    -0.59
    性和
    -0.59
    ,
    -0.58
     infatti
    -0.56
     jednak
    -0.47
    pri
    -0.46
     natomiast
    -0.42
    BaseController
    -0.42
     luat
    -0.42
    POSITIVE LOGITS
    存于互联网档案馆
    0.91
    abestanden
    0.84
    "?>
    0.81
    "):
    0.79
     Audiodateien
    0.78
    +:+
    0.77
    PerformLayout
    0.76
    Портал
    0.74
    RunWith
    0.72
    Portale
    0.72
    Activations Density 2.391%

    No Known Activations