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. 12-GEMMASCOPE-RES-16K
    6. 5262
    Prev
    Next
    INDEX
    Explanations

    references to success and efficacy in various contexts

    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
     سرو
    -0.52
     MATTER
    -0.52
    Addi
    -0.51
     Addi
    -0.51
    ignants
    -0.50
     Bourgoin
    -0.50
    waren
    -0.49
     remind
    -0.49
    ELING
    -0.48
     المل
    -0.48
    POSITIVE LOGITS
     success
    1.48
     successes
    1.43
     SUCCESS
    1.43
     successful
    1.37
     Success
    1.34
     Successful
    1.24
    isSuccessful
    1.24
    successful
    1.23
    Success
    1.23
    SUCCESS
    1.22
    Activations Density 0.117%

    No Known Activations