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. 7-GEMMASCOPE-RES-16K
    6. 9554
    Prev
    Next
    INDEX
    Explanations

    desires and intentions expressed through the word "want."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Kini
    -0.73
     hindurch
    -0.70
     ранее
    -0.63
    FormTagHelper
    -0.62
     inference
    -0.62
    Autoritní
    -0.62
     méret
    -0.62
    บริการ
    -0.61
     Alternatively
    -0.60
     NDEBUG
    -0.60
    POSITIVE LOGITS
     want
    0.98
     wants
    0.87
     wanted
    0.84
     must
    0.72
     wanna
    0.71
     always
    0.65
    Give
    0.64
     quiero
    0.64
     should
    0.64
     sure
    0.63
    Activations Density 0.160%

    No Known Activations