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. 3-GEMMASCOPE-RES-16K
    6. 9353
    Prev
    Next
    INDEX
    Explanations

    references to the name "Levine" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LikeLike
    -0.92
    findpost
    -0.89
    AddHtmlAttribute
    -0.83
     MessageBoxIcon
    -0.80
     BoxDecoration
    -0.75
     disambiguazione
    -0.74
    Tikang
    -0.74
    inthians
    -0.69
     assurent
    -0.68
     faim
    -0.68
    POSITIVE LOGITS
    Le
    2.54
     le
    2.53
     Le
    2.52
    le
    2.36
    LE
    2.18
     LE
    2.17
     Ле
    1.43
    Ле
    1.27
     ле
    1.25
    ле
    1.23
    Activations Density 0.123%

    No Known Activations