© 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
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 5046
    Prev
    Next
    INDEX
    Explanations

    determiners and articles in various contexts

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

    Token "A" followed by various words

    np_acts-logits-general · gemini-2.0-flash

    "A" followed by noun or programming term

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.57
    pausal
    -0.46
    queles
    -0.44
     mxArray
    -0.42
     vainqueur
    -0.41
     Krakowie
    -0.41
     abuelo
    -0.40
     campamento
    -0.40
     Eingang
    -0.38
    település
    -0.38
    POSITIVE LOGITS
    AutoScaleMode
    0.51
    SuspendLayout
    0.46
     guide
    0.46
     tribute
    0.45
     tale
    0.45
    colgroup
    0.44
     setuptools
    0.44
    メモ
    0.43
     Guide
    0.43
    Composable
    0.42
    Activations Density 0.318%

    No Known Activations