© 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. 8307
    Prev
    Next
    INDEX
    Explanations

    references to event handling and asynchronous processes in code

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

    Followed by "preventDefault" or related event handling methods

    np_acts-logits-general · gemini-2.0-flash

    prevent default event actions

    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
     Normdatei
    -1.16
    SceneManagement
    -0.82
    UnsafeEnabled
    -0.80
    RegressionTest
    -0.77
    WebServlet
    -0.77
    XmlAccessType
    -0.74
     '\\;'
    -0.73
    homonymie
    -0.73
     насељу
    -0.73
    Referències
    -0.71
    POSITIVE LOGITS
     final
    0.49
     raw
    0.45
     original
    0.44
     hot
    0.44
     dry
    0.44
    دام
    0.42
     magn
    0.42
    besch
    0.41
     co
    0.40
    OWSKI
    0.40
    Activations Density 0.123%

    No Known Activations