© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 3096
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the provision of conditions or parameters in mathematical contexts

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

    "given" and subsequent mathematical symbols or phrases

    np_acts-logits-general · gemini-2.0-flash

    given context

    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
    itemType
    -0.46
    ochond
    -0.46
    traceback
    -0.44
    tyl
    -0.44
     ujednoznacz
    -0.44
     juſ
    -0.42
    ſelves
    -0.42
    autoload
    -0.42
    salud
    -0.42
    ulz
    -0.42
    POSITIVE LOGITS
     given
    1.95
    given
    1.87
     Given
    1.78
    Given
    1.77
     GIVEN
    1.59
     dado
    1.13
     dadas
    1.06
     Dado
    1.05
     donné
    1.05
    Dado
    1.03
    Activations Density 0.375%

    No Known Activations