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. 5-GEMMASCOPE-RES-16K
    6. 13481
    Prev
    Next
    INDEX
    Explanations

    references to the concept of access and its different forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Umum
    -0.73
     devriez
    -0.68
     mû
    -0.66
    avocat
    -0.66
    iyle
    -0.66
     Locomotive
    -0.65
    mcg
    -0.64
     sauter
    -0.62
     viewModel
    -0.62
     carburetor
    -0.62
    POSITIVE LOGITS
     access
    2.54
     Access
    2.40
    Access
    2.31
    access
    2.30
     ACCESS
    2.18
    ACCESS
    2.13
     accesses
    2.03
     acess
    1.81
     acces
    1.73
     accessed
    1.61
    Activations Density 0.068%

    No Known Activations