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

    Neuronpedia

    Jacobian LensNEW
    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
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 11414
    Prev
    Next
    INDEX
    Explanations

    common conjunctions and prepositions in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -1.37
     Савезне
    -1.32
    Personendaten
    -1.29
    tagHelperRunner
    -1.28
     للاسماء
    -1.15
     ब्रेकडाउन
    -1.09
    цездатний
    -1.08
    oa̍t
    -1.07
     autorytatywna
    -1.07
    AddTagHelper
    -1.05
    POSITIVE LOGITS
    ’
    0.75
    '
    0.55
     this
    0.53
     as
    0.51
     while
    0.49
     so
    0.47
     according
    0.47
     the
    0.46
     we
    0.46
     these
    0.44
    Activations Density 1.640%

    No Known Activations