© 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. 2164
    Prev
    Next
    INDEX
    Explanations

    phrases involving actions and transitions related to dressing or undressing

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

    followed by past tense verbs

    np_acts-logits-general · gemini-2.0-flash

    and action verb

    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
    StoryboardSegue
    -0.57
    UnusedPrivate
    -0.56
    Према
    -0.55
    Personensuche
    -0.55
    byshev
    -0.54
     idén
    -0.54
    zzling
    -0.53
     interference
    -0.52
    indexing
    -0.51
     textStatus
    -0.51
    POSITIVE LOGITS
    MENAFN
    0.74
     become
    0.72
    DataAnnotations
    0.67
     let
    0.66
     slowly
    0.62
    Zeneca
    0.59
     تانيه
    0.59
     put
    0.59
    ませんか
    0.58
     began
    0.57
    Activations Density 0.371%

    No Known Activations