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. 13277
    Prev
    Next
    INDEX
    Explanations

    requests for opportunities or information

    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
    WriteTagHelper
    -1.16
     myſelf
    -0.86
     itſelf
    -0.83
    ništvo
    -0.81
     Majefty
    -0.80
     nahilalakip
    -0.79
     препратки
    -0.79
    ConstraintMaker
    -0.76
    AfterClass
    -0.76
     Akismet
    -0.74
    POSITIVE LOGITS
     Seeking
    1.12
     seeking
    1.06
    Seeking
    1.03
    seeking
    0.99
    Seek
    0.94
     searching
    0.93
     seek
    0.92
     seeks
    0.92
     mencari
    0.91
     search
    0.90
    Activations Density 0.085%

    No Known Activations