© 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. 22-GEMMASCOPE-RES-16K
    6. 13635
    Prev
    Next
    INDEX
    Explanations

    references to guest appearances and notable personalities in media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "guest" or "guests"

    np_acts-logits-general · gemini-2.0-flash

    guest roles and speakers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.69
    PerformLayout
    -0.65
    Portale
    -0.61
    AsStream
    -0.55
     HasFactory
    -0.51
     AppBundle
    -0.51
    +#+#
    -0.49
    czo
    -0.48
     ascenso
    -0.48
    lapsingToolbar
    -0.48
    POSITIVE LOGITS
     guest
    2.94
     Guest
    2.56
    guest
    2.50
    Guest
    2.49
     guests
    2.34
     GUEST
    2.26
    GUEST
    2.16
     Guests
    2.10
    guests
    1.96
    Guests
    1.92
    Activations Density 0.273%

    No Known Activations