© 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. 18-GEMMASCOPE-RES-16K
    6. 8018
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving variables and operations

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

    Multiplication, subtraction, and derivatives in mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions with variables

    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
    inda
    -0.52
    lec
    -0.51
    ele
    -0.49
     material
    -0.49
     hermanas
    -0.48
     autorytatywna
    -0.47
    Def
    -0.47
    entle
    -0.47
    Co
    -0.46
     Material
    -0.46
    POSITIVE LOGITS
    tableFuture
    0.83
    Personensuche
    0.82
    stdc
    0.78
     myſelf
    0.77
     LUMP
    0.74
     समीक्षाओं
    0.73
    بوابة
    0.70
     وتسجيلات
    0.69
    DeleteBehavior
    0.67
    下载附件
    0.67
    Activations Density 1.901%

    No Known Activations