© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12334
    Prev
    Next
    INDEX
    Explanations

    instances of the letter 'i' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    thasone
    -0.59
     læng
    -0.59
    étoit
    -0.57
     BoxFit
    -0.56
    تقاوى
    -0.56
     صوتيه
    -0.56
     beina
    -0.53
    URLException
    -0.52
     royaltyfri
    -0.52
    tgär
    -0.52
    POSITIVE LOGITS
    I
    1.13
     i
    1.02
     I
    1.02
    i
    1.00
    iI
    0.77
    ii
    0.66
    iii
    0.63
    I
    0.57
    <bos>
    0.57
     Ii
    0.57
    Activations Density 0.262%

    No Known Activations