© 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. 3348
    Prev
    Next
    INDEX
    Explanations

    references to data gathering and accuracy in medical or scientific contexts

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

    Gathering, collecting, or containing information/data

    np_acts-logits-general · gemini-2.0-flash

    acquiring information and data

    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
    InjectAttribute
    -0.62
    PhysRev
    -0.58
    TestingModule
    -0.53
    BrowserModule
    -0.52
    tagHelperRunner
    -0.52
    DeleteBehavior
    -0.51
    pyl
    -0.47
    cshtml
    -0.47
     AssemblyProduct
    -0.47
    nasel
    -0.46
    POSITIVE LOGITS
     information
    2.64
    information
    2.25
     info
    2.10
     informations
    2.02
     información
    1.98
    Information
    1.90
     Information
    1.85
     INFORMATION
    1.84
     informazioni
    1.79
     informatie
    1.79
    Activations Density 0.499%

    No Known Activations