© 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. 4549
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data processing and management

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

    after symbols or punctuation

    np_acts-logits-general · gemini-2.0-flash

    code, libraries, technical terms

    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
    AddTagHelper
    -0.69
     snippetHide
    -0.58
     שוליים
    -0.54
     makeStyles
    -0.53
    ReusableCell
    -0.53
     client
    -0.52
    ově
    -0.50
    OHN
    -0.50
    UnusedPrivate
    -0.50
     pre
    -0.49
    POSITIVE LOGITS
     BioLib
    0.60
    SqlClient
    0.55
    CodeAnalysis
    0.54
     metav
    0.53
     Sciento
    0.52
    bodyParser
    0.52
    !(:
    0.51
     referenties
    0.50
    Handlung
    0.50
    mobileqq
    0.50
    Activations Density 0.150%

    No Known Activations