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. 3686
    Prev
    Next
    INDEX
    Explanations

    equality and comparison operators in code

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

    Equality and inequality operators

    np_acts-logits-general · gemini-2.0-flash

    == and != operators or null

    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
     lenker
    -0.61
     שוליים
    -0.59
    ありますが
    -0.54
    inburgh
    -0.54
    ništ
    -0.52
     kasarigan
    -0.51
    あり
    -0.50
    zzi
    -0.49
     HasFactory
    -0.49
     говоря
    -0.49
    POSITIVE LOGITS
    ")==
    0.96
    ']==
    0.89
    withstanding
    0.85
     ==
    0.85
    )==
    0.83
    ================
    0.82
    ]==
    0.81
    rzost
    0.78
    Initializable
    0.76
    Xna
    0.71
    Activations Density 0.055%

    No Known Activations