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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 21893
    Prev
    Next
    INDEX
    Explanations

    phrases and words that convey appreciation, significance, or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    leading to, absolutely beautiful, thanks to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -0.66
     nahilalakip
    -0.56
    AndEndTag
    -0.52
    middels
    -0.45
     verschillen
    -0.44
     zijne
    -0.42
     Verpackung
    -0.42
    wijl
    -0.40
    principalTable
    -0.39
     wystarczy
    -0.39
    POSITIVE LOGITS
    AnchorTagHelper
    0.49
     GenerationType
    0.46
    NamedQueries
    0.46
    astify
    0.44
     sari
    0.44
     sni
    0.42
    Pul
    0.42
    BufferException
    0.42
     simula
    0.41
     surla
    0.41
    Activations Density 0.006%

    No Known Activations