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. 18-GEMMASCOPE-RES-16K
    6. 10487
    Prev
    Next
    INDEX
    Explanations

    propositions and conditional statements involving elements and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.67
    StoryboardSegue
    -0.66
     Meksiku
    -0.62
    elcome
    -0.57
     صوتيه
    -0.57
     bağlantılar
    -0.54
     ]}
    -0.53
     חיצוניים
    -0.51
    zarchiwizowane
    -0.50
    ))^{
    -0.50
    POSITIVE LOGITS
     say
    2.85
    say
    2.57
    Say
    2.22
     Say
    2.18
     SAY
    1.98
    SAY
    1.71
     sagen
    1.28
     says
    1.26
     bijvoorbeeld
    1.22
     misalnya
    1.19
    Activations Density 0.664%

    No Known Activations