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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3328
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "current" in various contexts

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

    "current"

    np_acts-logits-general · gemini-2.0-flash

    current state or value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NgModule
    -0.40
    swire
    -0.40
     scrollView
    -0.37
    URLException
    -0.36
     Pew
    -0.36
    vų
    -0.35
     getService
    -0.34
     SqlDbType
    -0.34
     deleteById
    -0.34
     Boli
    -0.33
    POSITIVE LOGITS
    current
    1.01
    Current
    0.83
     Current
    0.82
     current
    0.81
    CURRENT
    0.81
    getCurrent
    0.79
     CURRENT
    0.77
    curr
    0.73
    selected
    0.73
    setCurrent
    0.73
    Activations Density 0.320%

    No Known Activations