© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15258
    Prev
    Next
    INDEX
    Explanations

    variations of the word "handle" in various contexts

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

    Texts containing "handle" or "handling"

    np_acts-logits-general · gemini-2.0-flash

    handle / handles / handled / handling

    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
     PLWABN
    -0.62
    StoryboardSegue
    -0.62
     aloud
    -0.59
     BoxFit
    -0.58
     lærer
    -0.58
    ỡng
    -0.58
    ież
    -0.57
     vĩnh
    -0.57
    AndroidJUnit
    -0.56
    wiście
    -0.55
    POSITIVE LOGITS
     Handles
    1.21
     handles
    1.19
     handle
    1.08
     Handle
    1.06
     handled
    1.05
    handles
    1.04
     dealt
    1.04
     HANDLE
    1.01
    Handles
    0.98
    handled
    0.96
    Activations Density 0.119%

    No Known Activations