© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 643
    Prev
    Next
    INDEX
    Explanations

    text-related elements and structures

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

    Tokens relating to text and data

    np_acts-logits-general · gemini-2.0-flash

    text content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -1.02
    TagMode
    -0.79
    AndEndTag
    -0.79
     CreateTagHelper
    -0.78
     MainAxisSize
    -0.77
     المعيارى
    -0.75
     يتيمه
    -0.73
    DoubleQuotes
    -0.72
    تقاوى
    -0.70
     transférez
    -0.69
    POSITIVE LOGITS
    text
    0.45
     text
    0.41
    TextNode
    0.36
    Content
    0.36
    Text
    0.34
     texte
    0.33
     textes
    0.33
     тек
    0.32
     Utara
    0.32
     kimi
    0.32
    Activations Density 0.158%

    No Known Activations