© 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. 9022
    Prev
    Next
    INDEX
    Explanations

    high-frequency occurrences of specific phrases or terms

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

    "parameters", "options", or "field" after "The"/"the"

    np_acts-logits-general · gemini-2.0-flash

    the [noun]

    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
    
    -0.91
     betweenstory
    -0.76
    uttavia
    -0.72
     estekak
    -0.72
    nocześnie
    -0.65
     Italijanski
    -0.64
    =$?
    -0.62
     ModelRenderer
    -0.61
    latego
    -0.61
    حياتها
    -0.61
    POSITIVE LOGITS
     تضيفلها
    0.70
     Chwiliwch
    0.63
    sterious
    0.57
    seiti
    0.55
    ndre
    0.55
    </em>
    0.54
     بيها
    0.54
    matic
    0.53
    zeitige
    0.52
    tain
    0.51
    Activations Density 0.421%

    No Known Activations