© 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. 13242
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to recommendations and advice regarding moving and packing

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

    Actions done "self" or "independently"

    np_acts-logits-general · gemini-2.0-flash

    self-performed actions

    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
     Dens
    -0.56
    loroethane
    -0.54
    roides
    -0.53
     كره
    -0.51
    okok
    -0.50
    verständlich
    -0.49
    Espa
    -0.48
    ɜ
    -0.48
    disambiguation
    -0.48
    Dens
    -0.47
    POSITIVE LOGITS
     self
    1.82
     самостоятельно
    1.78
     zelf
    1.75
     yourself
    1.73
     himself
    1.71
    self
    1.70
     sendiri
    1.68
     themselves
    1.66
    自己
    1.61
     herself
    1.61
    Activations Density 0.519%

    No Known Activations