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. 2-GEMMASCOPE-RES-16K
    6. 14985
    Prev
    Next
    INDEX
    Explanations

    instances of the word "mini" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    JsonProperty
    -0.63
    upuncture
    -0.58
    JspWriter
    -0.57
     ActionListener
    -0.57
     WebDriverWait
    -0.55
    DispatchToProps
    -0.53
    coltà
    -0.52
     upvoted
    -0.52
     useState
    -0.51
    ₿
    -0.51
    POSITIVE LOGITS
     mini
    3.17
     Mini
    3.14
    Mini
    3.13
    mini
    2.95
     MINI
    2.76
    MINI
    2.65
     miniature
    2.30
     Miniature
    2.06
     Minis
    2.04
    miniature
    1.97
    Activations Density 0.060%

    No Known Activations