© 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. 19-GEMMASCOPE-RES-16K
    11. 3709
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possibility, potential, and considerations for improvement or modification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     presumably
    -0.94
     obviously
    -0.92
     evidently
    -0.92
     undoubtedly
    -0.91
     basically
    -0.90
    presumably
    -0.85
     usually
    -0.85
     doubtless
    -0.85
     definitely
    -0.82
    basically
    -0.82
    POSITIVE LOGITS
     depending
    1.06
    depending
    0.97
     jopa
    0.96
     someday
    0.93
     algún
    0.92
    anskje
    0.91
     some
    0.89
     might
    0.83
    Depending
    0.82
     algunos
    0.80
    Activations Density 0.601%

    No Known Activations