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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 10213
    Prev
    Next
    INDEX
    Explanations

    conditions related to device performance and errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    цездатний
    -0.57
     smtplib
    -0.51
    μί
    -0.50
    ]")]
    -0.50
    idemia
    -0.50
    štu
    -0.50
    seteq
    -0.49
     vermis
    -0.48
     Roskov
    -0.48
    etragen
    -0.47
    POSITIVE LOGITS
     restart
    1.07
     reboot
    1.03
     restarting
    1.02
     restarts
    0.98
     Restart
    0.96
     restarted
    0.95
     rebo
    0.94
     force
    0.92
     shut
    0.89
     quit
    0.88
    Activations Density 0.392%

    No Known Activations