© 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. 4121
    Prev
    Next
    INDEX
    Explanations

    coding elements related to functions and data handling

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

    Text between delimiters/boundaries

    np_acts-logits-general · gemini-2.0-flash

    between words and ranges

    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
     EconPapers
    -0.74
     CreateTagHelper
    -0.71
     فريبيس
    -0.65
    Билгалдахарш
    -0.65
     otomatig
    -0.60
     TType
    -0.53
    LETON
    -0.52
    tanleria
    -0.52
     tartalomajánló
    -0.51
    SharedCtor
    -0.50
    POSITIVE LOGITS
     between
    1.26
     until
    1.21
    between
    1.18
    Between
    1.15
    Until
    1.11
     jusqu
    1.10
     Between
    1.10
     BETWEEN
    1.08
    until
    1.08
     mellan
    1.07
    Activations Density 1.007%

    No Known Activations