© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1779
    Prev
    Next
    INDEX
    Explanations

    commands or prompts related to expanding content

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

    Preceding "expand" or "Category"

    np_acts-logits-general · gemini-2.0-flash

    Category / expand links

    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
    ,
    -0.46
    -0.39
     Landes
    -0.39
    -0.38
     //
    -0.38
     (
    -0.38
    ʺ
    -0.38
    strophy
    -0.35
    Rude
    -0.35
    perti
    -0.35
    POSITIVE LOGITS
     kasarigan
    1.15
    tvguidetime
    1.13
     متعلقه
    1.12
     مشين
    1.06
     NSCoder
    1.04
     myſelf
    1.04
     Theſe
    0.98
     Anſ
    0.96
     itſelf
    0.96
     дописавши
    0.96
    Activations Density 0.020%

    No Known Activations