© 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. 12524
    Prev
    Next
    INDEX
    Explanations

    lines that contain mathematical operations or symbols

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

    Code build directives and table formatting

    np_acts-logits-general · gemini-2.0-flash

    +build markers

    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
    __':
    -0.72
     initComponents
    -0.71
    __":
    
    -0.71
    bootstrapcdn
    -0.71
    __":
    -0.61
    Autoritní
    -0.60
    BeginContext
    -0.59
    Hawks
    -0.59
    ;'>
    -0.57
    })));
    -0.56
    POSITIVE LOGITS
    /−
    1.17
    &+
    1.10
    ++++++++++++++++
    1.09
    _+
    0.98
    ++++++++
    0.92
    +++
    0.88
    ++++
    0.87
    +++++
    0.82
     (+)
    0.79
     $+\
    0.78
    Activations Density 0.416%

    No Known Activations