© 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. 2-GEMMASCOPE-RES-16K
    11. 14501
    Prev
    Next
    INDEX
    Explanations

    terminology related to legal responsibility and paternity issues

    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
    <bos>
    -2.11
    pośred
    -0.61
    ekš
    -0.60
     שח
    -0.58
    rozum
    -0.57
     duyg
    -0.57
    vény
    -0.57
    ział
    -0.56
     الاول
    -0.55
    ítmény
    -0.54
    POSITIVE LOGITS
    zelfde
    0.79
    sweise
    0.71
    ième
    0.66
    iffance
    0.65
     tartalomajánló
    0.64
     يتيمه
    0.63
    iyle
    0.63
    enchymal
    0.61
     contextLoads
    0.60
    нным
    0.60
    Activations Density 2.687%

    No Known Activations