© 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. 7-GEMMASCOPE-RES-16K
    6. 3288
    Prev
    Next
    INDEX
    Explanations

    references to consistency and uniformity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelper
    -0.71
    PMailer
    -0.66
    ➟
    -0.63
     Petru
    -0.62
    ldt
    -0.62
    ########.
    -0.61
    serializers
    -0.60
     Wayback
    -0.58
    PreExecute
    -0.58
     JsonResponse
    -0.57
    POSITIVE LOGITS
     uniformity
    1.51
     uniform
    1.49
    Uniform
    1.34
    uniform
    1.33
     unif
    1.30
     uniformes
    1.30
     Uniform
    1.29
     uniforme
    1.24
    unified
    1.23
    统一
    1.22
    Activations Density 0.185%

    No Known Activations