© 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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11448
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their properties, particularly acids and their effects in reactions

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

    acids and chemical compounds

    np_acts-logits-general · gemini-2.0-flash

    chemical acids

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    ollectionView
    -0.54
    SuspendLayout
    -0.52
    ThemeProvider
    -0.48
    shortcuts
    -0.47
     referenties
    -0.46
     MessageBoxIcon
    -0.46
    ("'"
    -0.45
     babys
    -0.45
     Akismet
    -0.44
     propOrder
    -0.44
    POSITIVE LOGITS
     acid
    1.28
     acids
    1.15
     Acid
    1.08
    acid
    1.03
    Acid
    0.96
     Acids
    0.94
     ACID
    0.93
     ácido
    0.91
    acids
    0.90
     ácidos
    0.90
    Activations Density 0.310%

    No Known Activations