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. 6-GEMMASCOPE-RES-16K
    6. 4660
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to preparation and readiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Moll
    -0.79
    idth
    -0.75
    eez
    -0.72
    ‚¬
    -0.69
    EObject
    -0.68
    Viitteet
    -0.65
    Accessors
    -0.64
    googleapis
    -0.64
     GoogleFonts
    -0.64
    stateProvider
    -0.63
    POSITIVE LOGITS
     preparations
    2.06
     preparation
    2.05
     prepared
    1.96
     prepare
    1.92
     Preparations
    1.92
     prepares
    1.91
     Preparing
    1.91
     preparing
    1.90
     Prepare
    1.89
     Preparation
    1.88
    Activations Density 0.070%

    No Known Activations