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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9257
    Prev
    Next
    INDEX
    Explanations

    web-related components and framework references

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

    After a period or within file paths

    np_acts-logits-general · gemini-2.0-flash

    System.Web, Federal Reserve, NY

    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
    endphp
    -0.57
     HttpNotFound
    -0.47
    AddTo
    -0.44
    Sign
    -0.44
     campa
    -0.44
     nakalista
    -0.43
    μί
    -0.42
    艋
    -0.42
    +#+#
    -0.42
     career
    -0.42
    POSITIVE LOGITS
    AnchorStyles
    0.78
    bind
    0.68
    client
    0.64
     évolu
    0.56
    twimg
    0.56
    Diwedd
    0.55
    servlet
    0.54
    contentLoaded
    0.53
     CreateTagHelper
    0.53
    Portale
    0.53
    Activations Density 0.109%

    No Known Activations