Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10499
    Prev
    Next
    INDEX
    Explanations

    references to specific academic institutions and their associated departments or research areas

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

    Abbreviations for species, often italicized and followed by a period

    np_acts-logits-general · gemini-2.0-flash

    Hong Kong Bender Pathologists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.60
     conséquent
    -0.44
    ModelAdmin
    -0.41
    execSQL
    -0.39
    Stars
    -0.39
     barat
    -0.38
     cetera
    -0.38
     coba
    -0.38
    ①
    -0.38
    ample
    -0.37
    POSITIVE LOGITS
    gonic
    0.70
    EndInit
    0.67
    AddHtmlAttribute
    0.67
     useStyles
    0.67
     EnglishChoose
    0.66
    RTSN
    0.65
     صوتيه
    0.64
    حياتها
    0.64
     виправивши
    0.62
     CFC
    0.62
    Activations Density 0.635%

    No Known Activations