Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 67547
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "job" and related terms in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     CreateTagHelper
    -0.52
     rallado
    -0.51
    存于互联网档案馆
    -0.48
     Geografía
    -0.46
    IActionResult
    -0.46
    UnknownFieldSet
    -0.45
     Photocase
    -0.45
     ویکی‌پدیای
    -0.44
     ThemeData
    -0.44
    Fordítás
    -0.44
    POSITIVE LOGITS
    Rhestr
    0.52
    Exper
    0.46
    hef
    0.44
    ARL
    0.44
    internalType
    0.44
    moj
    0.44
     Palgrave
    0.43
    Specialist
    0.43
     Mob
    0.43
    Organ
    0.43
    Activations Density 0.001%

    No Known Activations