© 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. 27-GEMMASCOPE-RES-16K
    11. 12313
    Prev
    Next
    INDEX
    Explanations

    instances of positivity and appreciation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↘
    -0.41
    BorderSize
    -0.35
     Its
    -0.34
    IsContent
    -0.33
    更
    -0.33
     exquis
    -0.33
     Leur
    -0.32
    sigkeit
    -0.32
     themselves
    -0.32
    博物
    -0.31
    POSITIVE LOGITS
     kasarigan
    0.68
    writerow
    0.52
     betweenstory
    0.52
     člověk
    0.51
     AssemblyCompany
    0.51
    CloseOperation
    0.49
     nip
    0.48
     wade
    0.46
    来看看
    0.46
    gsSP
    0.45
    Activations Density 0.246%

    No Known Activations