© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5749
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and its applications in various contexts

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

    following "air" or related to "air"

    np_acts-logits-general · gemini-2.0-flash

    thin air and fresh air

    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
    DockStyle
    -0.65
    WebServlet
    -0.54
    StoreMessageInfo
    -0.50
    बर
    -0.45
     religieux
    -0.44
    Underline
    -0.44
     dė
    -0.44
    円
    -0.43
    EndGlobalSection
    -0.42
    </thead>
    -0.42
    POSITIVE LOGITS
     air
    3.63
    air
    3.08
    Air
    2.87
     Air
    2.86
     AIR
    2.65
    AIR
    2.50
     aire
    2.28
     Luft
    2.19
     lucht
    2.12
    空气
    2.10
    Activations Density 0.246%

    No Known Activations