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. 24-GEMMASCOPE-RES-16K
    6. 14020
    Prev
    Next
    INDEX
    Explanations

    elements related to structured data definitions and object properties

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

    Follows common separators or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    geographical locations

    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
    parsedMessage
    -0.60
    omock
    -0.56
    Искәрмәләр
    -0.48
    expandindo
    -0.47
    SequentialGroup
    -0.47
    发表于
    -0.44
     AudioClip
    -0.42
     الاطلاع
    -0.41
     privée
    -0.41
    θεια
    -0.40
    POSITIVE LOGITS
     city
    1.64
     country
    1.41
    city
    1.39
     City
    1.37
    City
    1.36
     cities
    1.28
     Country
    1.25
     province
    1.24
    country
    1.24
     town
    1.19
    Activations Density 0.334%

    No Known Activations