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. 13-GEMMASCOPE-RES-16K
    6. 8507
    Prev
    Next
    INDEX
    Explanations

    instances of statistical models and their respective evaluations or methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.90
     Efq
    -0.82
     poffible
    -0.81
     auroit
    -0.80
     étoit
    -0.79
     myſelf
    -0.79
     Majefty
    -0.79
    ^(@)
    -0.78
     beſt
    -0.77
    WriteTagHelper
    -0.76
    POSITIVE LOGITS
     
    0.68
     N
    0.54
     A
    0.52
     $\
    0.49
     G
    0.49
     O
    0.48
    na
    0.47
     M
    0.46
    กัน
    0.46
     “
    0.46
    Activations Density 0.070%

    No Known Activations