Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-GEMMASCOPE-RES-16K
    6. 11083
    Prev
    Next
    INDEX
    Explanations

    patterns involving the phrase "to be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.69
    ież
    -0.59
    didSet
    -0.55
     adiabatic
    -0.55
     Picchu
    -0.53
    worfen
    -0.52
    IntoConstraints
    -0.52
    AndEndTag
    -0.52
    etine
    -0.51
     REMEMBER
    -0.48
    POSITIVE LOGITS
    ſelf
    0.85
     itſelf
    0.85
    ſelves
    0.79
     Efq
    0.77
    =""></
    0.76
     Monfieur
    0.74
     purpoſe
    0.72
     myſelf
    0.72
    Бахар
    0.68
     Theſe
    0.66
    Activations Density 0.268%

    No Known Activations