© 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. 14977
    Prev
    Next
    INDEX
    Explanations

    expressions related to mathematical summations and conditions in equations

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

    Mathematical summations or products

    np_acts-logits-general · gemini-2.0-flash

    summation over

    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
     kasarigan
    -0.74
     <>",
    -0.63
    complexType
    -0.51
    MemoryWarning
    -0.50
    WebControls
    -0.50
     resourceCulture
    -0.48
     defaultstate
    -0.47
    JoinTable
    -0.47
     Interim
    -0.47
    usermodel
    -0.46
    POSITIVE LOGITS
     GetEnumerator
    0.88
    遍历
    0.58
     walk
    0.58
    Източници
    0.57
    *)((
    0.56
    PathVariable
    0.56
    遍
    0.56
     Wikimedijinoj
    0.53
     over
    0.53
    tizado
    0.52
    Activations Density 1.133%

    No Known Activations