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. 12-GEMMASCOPE-RES-16K
    6. 6192
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and their performance records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pageContext
    -0.59
     ujednoznacz
    -0.50
     поле
    -0.49
    cies
    -0.46
    Field
    -0.42
     hulk
    -0.41
    marginVertical
    -0.41
    hbs
    -0.40
    品的
    -0.40
    père
    -0.39
    POSITIVE LOGITS
    CloseOperation
    0.79
    ########.
    0.75
     estekak
    0.71
     autorytatywna
    0.69
     Giải
    0.65
    GeneratedCode
    0.64
     perennial
    0.64
    Geplaatst
    0.64
     iNdEx
    0.63
     anuales
    0.63
    Activations Density 0.180%

    No Known Activations