© 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. 14-GEMMASCOPE-RES-16K
    11. 3646
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possibility or feasibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AspNetCore
    -0.91
    PerformLayout
    -0.87
    SerializedSize
    -0.80
     sceptre
    -0.80
     autorytatywna
    -0.78
    Juven
    -0.76
    numerusform
    -0.76
    signia
    -0.76
     CURLOPT
    -0.75
     StatelessWidget
    -0.75
    POSITIVE LOGITS
     Possibility
    1.20
    POSSIBLE
    1.11
     POSSIBLE
    1.07
     possib
    1.06
     Possibilities
    1.05
    Possible
    1.03
     POSS
    1.01
     possibility
    1.01
     Possible
    1.00
     Möglich
    0.95
    Activations Density 0.068%

    No Known Activations