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. 7594
    Prev
    Next
    INDEX
    Explanations

    the frequency of the letter "m" 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 @ 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
    RetentionPolicy
    -0.74
    UnusedPrivate
    -0.72
    openConnection
    -0.67
     itſelf
    -0.67
     peric
    -0.64
     Divulgação
    -0.62
     parroquia
    -0.62
    WithIOException
    -0.62
    Portály
    -0.61
     دیکھیے
    -0.60
    POSITIVE LOGITS
     am
    1.45
     Im
    1.08
     Am
    1.07
    m
    1.02
     im
    0.95
    Iam
    0.91
    Am
    0.89
    Im
    0.89
    im
    0.87
     Ami
    0.83
    Activations Density 0.063%

    No Known Activations