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. 1749
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS class attributes in a web document

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

    Characters or symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical and code markers

    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
    ///</
    -0.53
     LUMP
    -0.52
    IVEREF
    -0.49
    ListModule
    -0.48
    Personendaten
    -0.46
    crisy
    -0.45
    adone
    -0.43
     histórica
    -0.43
    IsPostBack
    -0.41
     âm
    -0.41
    POSITIVE LOGITS
    DataAnnotations
    0.69
     indication
    0.68
    pexpr
    0.65
    NameLabel
    0.64
     Labels
    0.59
    ชื่อ
    0.59
     labels
    0.59
     defaultstate
    0.59
     numerals
    0.59
     contemporanea
    0.57
    Activations Density 0.134%

    No Known Activations