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. 14291
    Prev
    Next
    INDEX
    Explanations

    sequences of numeric values, particularly related to cell markers and immune responses

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

    "CD2"

    np_acts-logits-general · gemini-2.0-flash

    number 2 and following digits

    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
     autorytatywna
    -0.94
    ResumeLayout
    -0.91
     resourceCulture
    -0.86
     ComVisible
    -0.85
    */),
    -0.80
     McGovern
    -0.80
     Werth
    -0.78
     препратки
    -0.78
    LEIA
    -0.78
    Controllo
    -0.75
    POSITIVE LOGITS
    2
    1.47
    nd
    1.28
    0
    0.95
    3
    0.88
    4
    0.88
    1
    0.86
    5
    0.83
     thirds
    0.74
    8
    0.71
    thirds
    0.70
    Activations Density 1.980%

    No Known Activations