© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 12452
    Prev
    Next
    INDEX
    Explanations

    elements associated with programming or scripting languages, particularly related to data structures and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asuring
    -0.69
    éphane
    -0.68
     Parac
    -0.66
    ecute
    -0.65
    atific
    -0.63
     '+':
    -0.63
    HANG
    -0.62
     McC
    -0.61
     Lau
    -0.61
     Mus
    -0.61
    POSITIVE LOGITS
    EndContext
    0.74
    ⓧ
    0.70
     surla
    0.70
    MessageTagHelper
    0.68
     Numerade
    0.68
     ninjago
    0.67
    ่านั้น
    0.66
     SqlConnection
    0.66
    endphp
    0.63
     Enix
    0.63
    Activations Density 0.399%

    No Known Activations