© 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. 22-GEMMASCOPE-RES-16K
    11. 12678
    Prev
    Next
    INDEX
    Explanations

    structured data categories and references related to Wikipedia entries

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

    Wikipedia-related edits or references

    np_acts-logits-general · gemini-2.0-flash

    wikipedia references and articles

    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
    +#+
    -0.76
     ModelExpression
    -0.75
    NameInMap
    -0.67
    UnusedPrivate
    -0.64
    UpInside
    -0.60
    ThemeOverlay
    -0.60
    msgTypes
    -0.59
     سكانية
    -0.58
    enterOuterAlt
    -0.56
    Према
    -0.54
    POSITIVE LOGITS
     Wikipedia
    0.95
    wiki
    0.88
     article
    0.85
     Wiki
    0.83
     edit
    0.82
    wik
    0.82
     wiki
    0.81
     Wik
    0.79
     edits
    0.78
     articles
    0.77
    Activations Density 0.607%

    No Known Activations