© 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. 17-GEMMASCOPE-RES-16K
    11. 13701
    Prev
    Next
    INDEX
    Explanations

    references to decision-making and assessment processes in professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     weirdly
    -1.00
     goddamn
    -0.99
    Dunno
    -0.97
     disambiguazione
    -0.97
     dunno
    -0.97
     offenbar
    -0.94
     dodgy
    -0.94
     freilich
    -0.93
    :✨
    -0.92
     stuff
    -0.90
    POSITIVE LOGITS
     utilizing
    0.98
     posiada
    0.85
     utilize
    0.83
     utilized
    0.83
     می‌باشد
    0.82
     utilizes
    0.81
     данного
    0.81
    Utiliz
    0.80
     אשר
    0.80
     Utilizing
    0.76
    Activations Density 1.701%

    No Known Activations