Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 383
    Prev
    Next
    INDEX
    Explanations

    references to gaming and consoles, specifically related to the Xbox and its features

    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
    ConstraintMaker
    -0.56
    newtheorem
    -0.54
     Dik
    -0.51
     linkovi
    -0.51
    CIT
    -0.50
     Lub
    -0.48
    ərbaycan
    -0.48
    honey
    -0.48
     boiling
    -0.48
    hatic
    -0.47
    POSITIVE LOGITS
     Xbox
    1.24
     PlayStation
    1.22
     Playstation
    1.10
    Xbox
    1.09
     consoles
    1.08
     console
    1.06
    PlayStation
    1.05
     xbox
    1.00
    playstation
    0.98
     PS
    0.93
    Activations Density 0.117%

    No Known Activations