Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 12368
    Prev
    Next
    INDEX
    Explanations

    numbers and their combinations related to coding or data structures

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

    Follows punctuation or numbers

    np_acts-logits-general · gemini-2.0-flash

    petitioner income tax deficiency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.75
    Espèce
    -0.69
     gainera
    -0.67
    ganos
    -0.66
     BoxFit
    -0.65
    orianCalendar
    -0.63
    actéristique
    -0.62
    UIControlState
    -0.61
    Portail
    -0.61
    وأضاف
    -0.60
    POSITIVE LOGITS
    FTFY
    0.64
     voici
    0.51
    >{@
    0.50
    eseorang
    0.48
    InjectAttribute
    0.43
     afield
    0.43
     there
    0.42
    <sup>
    0.41
    rillation
    0.41
    nościo
    0.41
    Activations Density 0.372%

    No Known Activations