© 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. 5751
    Prev
    Next
    INDEX
    Explanations

    phrases related to secrecy or actions taking place away from public view

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

    Following "behind" or related to "closed"

    np_acts-logits-general · gemini-2.0-flash

    behind the scenes

    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
     Chwiliwch
    -0.66
    CppMethod
    -0.63
    Tikang
    -0.59
    MigrationBuilder
    -0.55
    DrawerToggle
    -0.50
    brido
    -0.48
    qrstuvwxyz
    -0.48
     alrededores
    -0.47
    헌
    -0.47
    Хьажоргаш
    -0.45
    POSITIVE LOGITS
     scenes
    1.28
     closed
    1.16
     Scenes
    1.06
    scenes
    1.03
    Scenes
    1.01
    closed
    0.94
     Closed
    0.93
     escena
    0.90
     curtain
    0.87
    Closed
    0.86
    Activations Density 0.069%

    No Known Activations