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
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 129930
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to scheduled events and their details

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

    events starting or beginning soon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.50
    AddTagHelper
    -0.43
    ことができました
    -0.41
     Exactos
    -0.39
     resourceCulture
    -0.38
    ſelves
    -0.38
    ivasan
    -0.34
    CheckBreak
    -0.33
     Extragalactic
    -0.33
     plufieurs
    -0.33
    POSITIVE LOGITS
     start
    2.41
     starts
    2.30
     started
    2.20
     begins
    2.14
     begin
    2.14
     starting
    2.05
     beginning
    2.02
     commence
    2.02
     commenced
    2.00
     commences
    1.99
    Activations Density 0.240%

    No Known Activations