© 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. 1670
    Prev
    Next
    INDEX
    Explanations

    quotations and statements from sources or individuals

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

    Text within quotation marks

    np_acts-logits-general · gemini-2.0-flash

    opening quotation or bracket

    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
     autorytatywna
    -0.90
     nahilalakip
    -0.82
    出版年
    -0.80
    WebVitals
    -0.78
     EconPapers
    -0.78
    MENAFN
    -0.75
     ويكيميديا
    -0.73
    )++;
    -0.70
    FormTagHelper
    -0.69
    SuspendLayout
    -0.69
    POSITIVE LOGITS
     “
    1.50
     "
    1.49
     "...
    1.44
     “…
    1.41
     “...
    1.30
    “
    1.24
    “…
    1.21
    “...
    1.20
     “[
    1.15
     "..
    1.15
    Activations Density 0.228%

    No Known Activations