© 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 EvalsExportsinterp-engineNEWAPI 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. 10775
    Prev
    Next
    INDEX
    Explanations

    references to legal and regulatory standards related to safety in the Czech Republic

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

    Czech language and related symbols

    np_acts-logits-general · gemini-2.0-flash

    Czech Republic

    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
    ंदीखरीदारी
    -0.89
     dítě
    -0.85
     tenisky
    -0.83
     plufieurs
    -0.83
    ConstraintMaker
    -0.82
    RegressionTest
    -0.81
    ⟬
    -0.80
     betweenstory
    -0.79
     Normdatei
    -0.78
    DockStyle
    -0.78
    POSITIVE LOGITS
     nad
    0.48
     „
    0.45
     z
    0.44
     pod
    0.42
     Š
    0.40
     sp
    0.40
     Czech
    0.40
    „
    0.37
     do
    0.36
     so
    0.36
    Activations Density 0.127%

    No Known Activations