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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 12865
    Prev
    Next
    INDEX
    Explanations

    XML tags and parameters related to project configuration files

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

    XML or configuration file attributes

    np_acts-logits-general · gemini-2.0-flash

    attribute assignment definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tigma
    -0.48
    телни
    -0.48
    hoea
    -0.47
    тка
    -0.47
    KommentareTeilen
    -0.47
     invece
    -0.47
    setupUi
    -0.47
    deinit
    -0.47
     __
    -0.46
    ",
    -0.46
    POSITIVE LOGITS
    GEBURTSDATUM
    0.85
    orianCalendar
    0.65
    tagHelperRunner
    0.64
     CreateTagHelper
    0.61
     مرئيه
    0.60
    ValueGeneration
    0.56
    urbed
    0.54
     mergeFrom
    0.53
    ulitis
    0.52
     Pří
    0.52
    Activations Density 0.447%

    No Known Activations