© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8392
    Prev
    Next
    INDEX
    Explanations

    phrases that start with "With" or related structures indicating conditions or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.96
    XmlAccessType
    -0.95
     виправивши
    -0.94
    Autoritní
    -0.89
     autorytatywna
    -0.84
     transférez
    -0.81
     disambiguazione
    -0.80
    unknownFields
    -0.80
    XmlAccessorType
    -0.78
    mybatisplus
    -0.78
    POSITIVE LOGITS
    With
    2.10
     With
    1.96
    WITH
    1.22
     WITH
    1.10
    Without
    1.00
    By
    0.99
     Avec
    0.97
    From
    0.96
     Without
    0.95
     Dengan
    0.93
    Activations Density 0.124%

    No Known Activations