© 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. 14-GEMMASCOPE-RES-16K
    11. 10476
    Prev
    Next
    INDEX
    Explanations

    structures related to data formatting or coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.90
     kasarigan
    -0.87
    rungsseite
    -0.85
    NameInMap
    -0.85
    <unused74>
    -0.83
    <unused8>
    -0.83
    <unused79>
    -0.83
    ロウィン
    -0.83
    <unused23>
    -0.83
    <unused41>
    -0.83
    POSITIVE LOGITS
     despite
    0.43
    Compared
    0.39
     hardly
    0.38
    Despite
    0.38
     compared
    0.37
    3
    0.37
     Grüsse
    0.36
    Half
    0.36
     Compared
    0.36
    Q
    0.36
    Activations Density 1.021%

    No Known Activations