© 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. 24-GEMMASCOPE-RES-16K
    6. 1433
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions structured around mathematical operations and inequalities

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

    Followed by closing parenthesis/brackets/braces in mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    right following closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    あれ
    -0.48
     Dank
    -0.46
     Criterion
    -0.46
    aarrggbb
    -0.44
    net
    -0.43
    online
    -0.43
     screen
    -0.43
     brick
    -0.42
    οντας
    -0.42
     block
    -0.42
    POSITIVE LOGITS
    .$
    1.01
    .$,
    0.95
    .$.
    0.85
    "],
    
    0.75
    .${
    0.73
    .\
    0.71
    .$$
    0.67
    )_{
    0.67
     مرئيه
    0.64
    ]=\
    0.63
    Activations Density 0.294%

    No Known Activations