© 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. 15468
    Prev
    Next
    INDEX
    Explanations

    terms related to camera equipment and photography techniques

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

    Canon cameras and photography

    np_acts-logits-general · gemini-2.0-flash

    Canon cameras and lenses

    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
    CSE
    -0.51
    CodeAnalysis
    -0.50
    WaitGroup
    -0.49
    figsize
    -0.49
    onActivityResult
    -0.49
    RoutingModule
    -0.46
     webdriver
    -0.45
     radi
    -0.45
     NgModule
    -0.45
     recher
    -0.44
    POSITIVE LOGITS
     Canon
    0.94
     Nikon
    0.84
    Canon
    0.83
     DSLR
    0.72
     camera
    0.72
     cameras
    0.72
     Olympus
    0.72
    sidemargin
    0.71
    Nikon
    0.71
     Nik
    0.68
    Activations Density 0.121%

    No Known Activations