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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2608
    Prev
    Next
    INDEX
    Explanations

    references to cosmetic procedures and their effects

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

    Follows prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    non

    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
    CELLANEOUS
    -0.65
    verwijspagina
    -0.59
    Obrázky
    -0.53
    psk
    -0.52
     makeStyles
    -0.51
     ThemeData
    -0.50
    soort
    -0.48
    kül
    -0.47
     AutoMapper
    -0.46
    ndice
    -0.45
    POSITIVE LOGITS
     ſy
    0.62
     Instantly
    0.59
     okam
    0.59
    Immediate
    0.59
    WriteTagHelper
    0.58
    دانشنامهٔ
    0.57
     instantly
    0.57
     clín
    0.56
     itſelf
    0.56
     pleaſure
    0.55
    Activations Density 0.060%

    No Known Activations