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. 16-GEMMASCOPE-RES-16K
    6. 12777
    Prev
    Next
    INDEX
    Explanations

    terms related to actions and their grammatical forms, particularly in verb phrases

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

    Code, programing, or file names

    np_acts-logits-general · gemini-2.0-flash

    programming keywords and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.65
    ⓧ
    -0.59
    InvalidProtocol
    -0.58
    queryInterface
    -0.57
    السكان
    -0.57
     handleMessage
    -0.54
    contentLoaded
    -0.54
    Frat
    -0.54
    richTextPanel
    -0.52
     pédagogique
    -0.52
    POSITIVE LOGITS
    <?
    0.65
    ếng
    0.55
    batore
    0.54
    ViewModels
    0.53
     viewDidLoad
    0.50
     виправивши
    0.50
    paddingVertical
    0.45
     dess
    0.45
    splatz
    0.44
    StreetMap
    0.44
    Activations Density 0.472%

    No Known Activations