Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1759
    Prev
    Next
    INDEX
    Explanations

    instances of the word "handle" in various contexts

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

    "Handle" or "handles" and related words

    np_acts-logits-general · gemini-2.0-flash

    handling or manipulating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.69
     PLWABN
    -0.60
    rigal
    -0.59
     ProductService
    -0.59
     surla
    -0.58
     vĩnh
    -0.56
    ież
    -0.56
    AsUp
    -0.55
    saraba
    -0.55
    wiście
    -0.55
    POSITIVE LOGITS
     Handles
    1.09
    handles
    1.04
     handles
    1.02
     Handle
    0.86
     handle
    0.85
    Handles
    0.83
     handled
    0.80
     HANDLE
    0.79
     dealt
    0.79
    handled
    0.76
    Activations Density 0.079%

    No Known Activations