© 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. 2238
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Ko" or related names in various contexts

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

    Text starting with "Ko" or "Koppen"

    np_acts-logits-general · gemini-2.0-flash

    words starting with Ko

    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
     Carsten
    -0.55
     Crick
    -0.49
    بالإنجليزية
    -0.48
    besch
    -0.47
     ciudadana
    -0.46
    HasOne
    -0.46
     desselben
    -0.45
    velli
    -0.45
     Charg
    -0.45
    AccessorTable
    -0.45
    POSITIVE LOGITS
     Ko
    0.86
    Ko
    0.84
     ko
    0.73
    Portale
    0.71
    OGND
    0.70
     Koe
    0.70
    LVANIA
    0.68
     Sko
    0.67
    archiviato
    0.65
     Trustee
    0.63
    Activations Density 0.049%

    No Known Activations