© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15393
    Prev
    Next
    INDEX
    Explanations

    keywords related to organizational structures and responses in various fields

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

    location

    np_acts-logits-general · gemini-2.0-flash

    locations or distribution

    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
     tartalomajánló
    -0.70
     Monfieur
    -0.65
    
    -0.64
    bewerken
    -0.64
     becauſe
    -0.64
     whoſe
    -0.63
     hereto
    -0.62
     nakalista
    -0.61
    Referanser
    -0.61
     insuffisamment
    -0.59
    POSITIVE LOGITS
     everywhere
    0.64
     partout
    0.64
     везде
    0.59
     überall
    0.57
     across
    0.53
    分别
    0.53
    everywhere
    0.53
     in
    0.51
     ovunque
    0.51
     versions
    0.50
    Activations Density 0.515%

    No Known Activations