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-2-9B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 15582
    Prev
    Next
    INDEX
    Explanations

    keywords associated with logical connections and formal structures in academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    таратура
    -0.43
    assertj
    -0.37
    intios
    -0.36
     ant
    -0.36
     OMIT
    -0.36
    enumi
    -0.35
     weather
    -0.35
    Cumulative
    -0.35
    География
    -0.34
    aktery
    -0.34
    POSITIVE LOGITS
     autorytatywna
    0.79
     acronym
    0.50
    RTDA
    0.50
    存于互联网档案馆
    0.49
    IUrlHelper
    0.47
    Autoritní
    0.47
    setupUi
    0.47
    RegressionTest
    0.46
     JAXBElement
    0.46
     EconPapers
    0.45
    Activations Density 2.318%

    No Known Activations