© 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 EvalsExportsinterp-engineNEWAPI 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. 10950
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate ease of use or simplicity in performing tasks

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

    Comes before actions or qualities

    np_acts-logits-general · gemini-2.0-flash

    ease of use and action

    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
    lihatkan
    -0.47
     presto
    -0.45
     libera
    -0.44
    IBOutlet
    -0.44
    ⓘ
    -0.44
     Riproduzione
    -0.43
     terci
    -0.42
     garan
    -0.41
     būt
    -0.41
     almo
    -0.40
    POSITIVE LOGITS
    @[+][
    0.81
    PreferredItem
    0.76
    parseFrom
    0.69
     handling
    0.67
     فريبيس
    0.66
    UnusedPrivate
    0.63
    MENAFN
    0.63
    tvguidetime
    0.62
    ovatel
    0.62
    handling
    0.62
    Activations Density 0.121%

    No Known Activations