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. 21-GEMMASCOPE-RES-16K
    6. 15138
    Prev
    Next
    INDEX
    Explanations

    instances of separation, both in context (such as structural separation in organizations) and in general references to dividing entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.77
    WebControls
    -0.55
    PerformLayout
    -0.49
     mulut
    -0.49
     BoxFit
    -0.49
     Consensus
    -0.48
     Filled
    -0.45
     Ajoutez
    -0.44
     AssemblyProduct
    -0.43
    expired
    -0.43
    POSITIVE LOGITS
     separation
    2.89
     separated
    2.69
     separating
    2.60
     separate
    2.58
     Separ
    2.57
     Separation
    2.54
     separates
    2.54
     Separate
    2.47
     seper
    2.47
     SEPAR
    2.46
    Activations Density 0.651%

    No Known Activations