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-2-9B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 135
    Prev
    Next
    INDEX
    Explanations

    terms related to competition and opposition in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.71
     CreateTagHelper
    -0.68
     zwiſchen
    -0.63
    GEBURTSDATUM
    -0.58
    haikusbot
    -0.58
    PageFactory
    -0.57
    namb
    -0.57
     AssemblyCulture
    -0.56
    getMinutes
    -0.56
     zuſammen
    -0.56
    POSITIVE LOGITS
     opponent
    1.51
     opponents
    1.48
     opposition
    1.41
     enemy
    1.26
     rival
    1.25
     opposing
    1.23
     rivals
    1.22
    opponent
    1.18
    Opposition
    1.14
     musuh
    1.14
    Activations Density 0.320%

    No Known Activations