© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1647
    Prev
    Next
    INDEX
    Explanations

    numerical values and descriptions related to statistics or data

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

    Numbers followed by larger numbers

    np_acts-logits-general · gemini-2.0-flash

    Japanese timestamps and code

    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
     الحره
    -1.06
    Personendaten
    -0.79
     EconPapers
    -0.77
    writeFieldEnd
    -0.76
    Diwedd
    -0.72
    CodedInputStream
    -0.70
     nakalista
    -0.68
     الرياضيه
    -0.68
    ScopeManager
    -0.67
    RegistryLite
    -0.67
    POSITIVE LOGITS
    upassen
    0.59
    gettimeofday
    0.48
    glClear
    0.48
    toDouble
    0.46
    mgren
    0.45
    peto
    0.45
    ţia
    0.44
    ământ
    0.44
    TestingModule
    0.42
    iyle
    0.41
    Activations Density 0.560%

    No Known Activations