© 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. 6787
    Prev
    Next
    INDEX
    Explanations

    components and functionalities related to event handling in user interface programming

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

    Code related to event listeners

    np_acts-logits-general · gemini-2.0-flash

    adding event listeners

    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
    tvguidetime
    -0.57
    HostException
    -0.52
     czo
    -0.48
    formKey
    -0.45
     ContentValues
    -0.44
    iomanip
    -0.44
    rmdir
    -0.43
    DebuggerNonUser
    -0.43
    たた
    -0.42
     CGRectMake
    -0.41
    POSITIVE LOGITS
     listener
    1.08
     listeners
    0.99
    addEventListener
    0.96
    listeners
    0.96
     listen
    0.94
     Listener
    0.93
     listens
    0.92
    Listener
    0.90
    EventListener
    0.90
     Listen
    0.88
    Activations Density 0.305%

    No Known Activations