© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2018
    Prev
    Next
    INDEX
    Explanations

    programming concepts or code structure elements related to functions and variable declarations

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

    Mathematical plus signs and related symbols

    np_acts-logits-general · gemini-2.0-flash

    `+` symbol and mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __*/
    -0.67
     School
    -0.56
    Бележки
    -0.53
    Diwedd
    -0.52
    Atsauces
    -0.52
    istoitu
    -0.51
    קישורים
    -0.50
     Faculty
    -0.50
    />";
    -0.49
    School
    -0.49
    POSITIVE LOGITS
    +
    0.79
    +:+
    0.70
     + 
    0.68
     +
    0.63
     plus
    0.61
    ＋
    0.61
    }+
    0.59
    +.
    0.58
    ²+
    0.57
     $+
    0.57
    Activations Density 0.271%

    No Known Activations