© 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. 11038
    Prev
    Next
    INDEX
    Explanations

    specific numerical and coded data

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

    Numbers or digits appearing in text

    np_acts-logits-general · gemini-2.0-flash

    numbers and punctuation

    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
     nahilalakip
    -0.72
    PyExc
    -0.67
    DoubleQuotes
    -0.67
     دیکھیے
    -0.66
    ,:]
    -0.64
    ,:),
    -0.64
     présidenti
    -0.61
    ])){
    -0.60
    SharedDtor
    -0.60
    }")
    
    -0.59
    POSITIVE LOGITS
    ExtendWith
    0.58
    surate
    0.53
     extinct
    0.52
    istique
    0.50
     Saltar
    0.49
     Assignee
    0.48
     Soud
    0.48
     onView
    0.48
    conic
    0.47
     surg
    0.46
    Activations Density 0.310%

    No Known Activations