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. 24-GEMMASCOPE-RES-16K
    6. 2340
    Prev
    Next
    INDEX
    Explanations

    phrases that describe specific actions or events occurring within a certain context or environment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "in order"

    np_acts-logits-general · gemini-2.0-flash

    in order to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.83
     disambiguazione
    -0.81
     Roskov
    -0.75
    hyrchwyd
    -0.73
    ForValue
    -0.73
     ExecuteAsync
    -0.72
    UnitTesting
    -0.69
    ContentAsync
    -0.68
    SourceChecksum
    -0.68
     betweenstory
    -0.68
    POSITIVE LOGITS
     order
    2.84
    order
    2.10
    Order
    1.76
     ORDER
    1.75
     Order
    1.73
    ORDER
    1.55
     hopes
    1.46
     orders
    1.31
     ordre
    1.31
     ordem
    1.30
    Activations Density 0.329%

    No Known Activations