© 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. 22-GEMMASCOPE-RES-16K
    11. 3555
    Prev
    Next
    INDEX
    Explanations

    elements related to object creation and initialization in programming

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

    after "new" keyword

    np_acts-logits-general · gemini-2.0-flash

    new programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    JSONException
    -0.78
     MotionEvent
    -0.70
     onAnimation
    -0.68
    DataSnapshot
    -0.65
    TargetException
    -0.64
    URLException
    -0.64
    ActionEvent
    -0.61
    MouseEvent
    -0.61
    +#+#
    -0.60
    HostException
    -0.60
    POSITIVE LOGITS
    Default
    0.86
    Simple
    0.79
    simple
    0.77
     تضيفلها
    0.76
     Default
    0.74
     Simple
    0.73
    default
    0.69
     simple
    0.68
     standaard
    0.66
     customised
    0.65
    Activations Density 0.341%

    No Known Activations