© 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. 21721
    Prev
    Next
    INDEX
    Explanations

    parentheses and dollar signs in code snippets or expressions

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

    number formatting or variables

    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
    Personendaten
    -0.65
    tershire
    -0.60
    wpi
    -0.59
    ⟬
    -0.58
    jooq
    -0.57
     $_"
    -0.57
    GroupLayout
    -0.56
    usermodel
    -0.56
    новништво
    -0.55
     viewDidLoad
    -0.53
    POSITIVE LOGITS
    (
    0.49
     brasileño
    0.40
     siglos
    0.39
     salmón
    0.38
     especias
    0.38
     kalau
    0.37
     vuotta
    0.37
     dulces
    0.37
     helados
    0.36
     hatta
    0.35
    Activations Density 0.011%

    No Known Activations