© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1844
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'j' or related phonetic elements

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

    Follows a one or two letter token

    np_acts-logits-general · gemini-2.0-flash

    dejuren, TJDO, bjork, ojb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    u
    -0.69
     relative
    -0.54
    ContentAsync
    -0.47
    an
    -0.46
    relative
    -0.44
    Segoe
    -0.43
    osene
    -0.43
     ont
    -0.41
    Unmarshal
    -0.41
     static
    -0.41
    POSITIVE LOGITS
    ьаж
    0.82
     Mij
    0.74
    SBATCH
    0.72
    حياته
    0.69
    حياتها
    0.69
    новниш
    0.69
    edrez
    0.68
     AppDelegate
    0.68
    MLLoader
    0.67
     AppBar
    0.67
    Activations Density 0.238%

    No Known Activations