© 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. 4117
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document or section, indicated by a specific marker

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

    preceding quotation marks

    np_acts-logits-general · gemini-2.0-flash

    start of sentence after punctuation

    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
    featureID
    -0.78
    Personendaten
    -0.74
    sidemargin
    -0.73
    OGND
    -0.69
    InitVars
    -0.68
    webElementXpaths
    -0.65
    kloped
    -0.60
     دیکھیے
    -0.58
    Попис
    -0.57
    XmlAccessorType
    -0.56
    POSITIVE LOGITS
     BoxDecoration
    0.79
     berupa
    0.67
     تضيفلها
    0.63
    mitives
    0.56
    ubin
    0.55
     الحره
    0.54
    ärzt
    0.53
     مرئيه
    0.52
     msglen
    0.52
    heritance
    0.52
    Activations Density 0.015%

    No Known Activations