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. 16190
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and their syntax in the text

    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
    <strong>
    -0.82
     sorte
    -0.81
    Paola
    -0.74
     Betracht
    -0.73
    CodeDom
    -0.73
    دانشنامهٔ
    -0.70
     mạch
    -0.69
     fede
    -0.68
     entanto
    -0.68
     rând
    -0.68
    POSITIVE LOGITS
    =\"
    2.20
    (\"
    1.53
     \"
    1.48
    \":\"
    1.38
    =\""
    1.28
     \"%
    1.18
    .\"
    1.16
    ("\"
    1.08
    {\"
    1.08
    \"
    1.06
    Activations Density 0.349%

    No Known Activations