© 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. 18-GEMMASCOPE-RES-16K
    6. 2496
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions and treatments

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

    Follows punctuation or sentence fragments

    np_acts-logits-general · gemini-2.0-flash

    was loaned to, effect null

    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
    contentLoaded
    -0.47
    theless
    -0.46
     unless
    -0.44
    Pois
    -0.43
     static
    -0.43
    JRadioButton
    -0.42
    прав
    -0.42
     depends
    -0.41
     дел
    -0.41
     problème
    -0.41
    POSITIVE LOGITS
    ########.
    0.83
     suddenly
    0.69
    TemporalType
    0.68
    farwyddwr
    0.67
     onCancelled
    0.67
    BeginContext
    0.65
     الحره
    0.65
    KommentareTeilen
    0.61
    endphp
    0.60
     instantly
    0.60
    Activations Density 0.025%

    No Known Activations