© 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. 37-GEMMASCOPE-RES-16K
    11. 2329
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional conflict and judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.72
    parsedMessage
    -0.67
     Biôgrafia
    -0.63
     eventdata
    -0.63
     صوتيه
    -0.60
    最快更新
    -0.59
    StructEnd
    -0.59
     GenerationType
    -0.59
    SBATCH
    -0.58
    principalColumn
    -0.58
    POSITIVE LOGITS
    ingly
    0.50
    fully
    0.41
    ably
    0.37
    istically
    0.36
     initComponents
    0.34
    tably
    0.33
    antly
    0.33
     cánh
    0.32
    ishly
    0.32
    iously
    0.29
    Activations Density 0.418%

    No Known Activations