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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 30372
    Prev
    Next
    INDEX
    Explanations

    literal representations of mathematical operations or expressions

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

    mathematical expressions and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )]);
    -0.66
    ']));
    -0.61
    AllAfrica
    -0.56
    "});
    -0.56
    "]));
    -0.56
    )}</
    -0.56
    出版年
    -0.55
    KURZBESCHREIBUNG
    -0.54
    AFM
    -0.54
    .[/
    -0.54
    POSITIVE LOGITS
    #
    0.74
     #
    0.68
    脚注の使い方
    0.63
    *
    0.58
     خارجية
    0.54
    /*
    0.54
    ##
    0.54
     *
    0.52
     
    0.52
    날
    0.50
    Activations Density 0.026%

    No Known Activations