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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 4544
    Prev
    Next
    INDEX
    Explanations

    words related to plumbing and its various aspects

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

    Tokens starting with "pl" or "Pl"

    np_acts-logits-general · gemini-2.0-flash

    words starting with pl

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.62
    hyrchwyd
    -0.60
    Tikang
    -0.59
    ElementType
    -0.58
    EDEFAULT
    -0.55
     rêver
    -0.54
     KeyError
    -0.54
     setw
    -0.53
    CROSSTALK
    -0.52
    存于互联网档案馆
    -0.51
    POSITIVE LOGITS
     للمعارف
    0.67
     Pl
    0.61
    ArrowToggle
    0.59
     otomatig
    0.57
    UserScript
    0.53
     ventre
    0.53
    Pl
    0.50
    AutoField
    0.49
    FORMS
    0.48
    URAL
    0.48
    Activations Density 0.158%

    No Known Activations