© 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. 9036
    Prev
    Next
    INDEX
    Explanations

    punctuation and specific function calls related to data manipulation

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

    Code snippets using pandas or similar libraries

    np_acts-logits-general · gemini-2.0-flash

    pandas DataFrame operations

    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
    IonicModule
    -0.50
    anak
    -0.46
    AnimationsModule
    -0.42
     invokingState
    -0.42
    cionario
    -0.42
    triangleright
    -0.41
    Ordinal
    -0.40
    WindowEvent
    -0.40
    かえ
    -0.40
     án
    -0.40
    POSITIVE LOGITS
     يتيمه
    0.78
    webElementXpaths
    0.74
    shape
    0.65
     shape
    0.62
    SourceChecksum
    0.61
    MessageOf
    0.61
     tambour
    0.58
    SuppressLint
    0.58
     Kidman
    0.57
     Ordovician
    0.57
    Activations Density 0.118%

    No Known Activations