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. 8328
    Prev
    Next
    INDEX
    Explanations

    references to cars and automotive topics

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

    after "car"

    np_acts-logits-general · gemini-2.0-flash

    car and associated terms

    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
    WriteTagHelper
    -0.75
    ########.
    -0.70
    +#+
    -0.65
    ftagPool
    -0.64
    Jeografia
    -0.61
    PageIndex
    -0.54
     '\\;'
    -0.54
    wandel
    -0.53
     disambiguazione
    -0.53
    ínű
    -0.51
    POSITIVE LOGITS
     owners
    0.71
     rental
    0.69
     owner
    0.65
    abinieri
    0.60
     rentals
    0.59
     Owners
    0.59
     wreck
    0.58
     ownership
    0.57
     nahilalakip
    0.55
     wrecks
    0.55
    Activations Density 0.234%

    No Known Activations