© 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. 6939
    Prev
    Next
    INDEX
    Explanations

    references to research studies and their findings

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

    Absence, lack, or missing elements

    np_acts-logits-general · gemini-2.0-flash

    lack of something

    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
    ValueStyle
    -0.68
    rungsseite
    -0.59
     pinulongan
    -0.56
    balleur
    -0.56
    Portale
    -0.53
     disambiguazione
    -0.51
     препратки
    -0.48
    越好
    -0.47
     للاسماء
    -0.47
    MigrationBuilder
    -0.46
    POSITIVE LOGITS
     absence
    1.96
     lack
    1.78
     Absence
    1.72
    absence
    1.67
     lacks
    1.64
    ไม่มี
    1.64
     lacked
    1.60
     lacking
    1.58
    Absence
    1.56
     devoid
    1.55
    Activations Density 1.656%

    No Known Activations