© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114994
    Prev
    Next
    INDEX
    Explanations

    mathematical references and notations in a formal context

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

    \[...\] section references

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     يتيمه
    -0.60
    RectangleBorder
    -0.52
     surla
    -0.52
    ModelAdmin
    -0.49
     defStyleAttr
    -0.48
     BoxFit
    -0.47
    PreExecute
    -0.46
     aDecoder
    -0.45
    gdx
    -0.45
     CanadaChoose
    -0.44
    POSITIVE LOGITS
    fromnode
    0.57
    帖最后由
    0.45
    әрмәләр
    0.43
    graphiques
    0.41
     CHAIR
    0.41
     justify
    0.40
     injected
    0.37
     slides
    0.37
     intro
    0.36
     quedado
    0.36
    Activations Density 1.096%

    No Known Activations