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. 18-GEMMASCOPE-RES-16K
    6. 1450
    Prev
    Next
    INDEX
    Explanations

    phrases related to the medication 'vasopressin' and its effects

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

    Tokens after "Vas" at the beginning of references or citations

    np_acts-logits-general · gemini-2.0-flash

    vasa, vasopressin, vasculitis, Waßmannsdorf

    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
    ponses
    -0.66
     Tang
    -0.65
    EqualsAnd
    -0.62
     GenerationType
    -0.62
     broche
    -0.61
    awtextra
    -0.60
    UIControlState
    -0.60
    IANGLES
    -0.60
     createSlice
    -0.59
    fromnode
    -0.58
    POSITIVE LOGITS
    wash
    0.61
    Wa
    0.61
    HasBeenSet
    0.55
    NameInMap
    0.55
     råd
    0.55
     Wa
    0.54
    xhtml
    0.54
     motivadoras
    0.53
    徊
    0.53
    ovas
    0.53
    Activations Density 0.106%

    No Known Activations