© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 10378
    Prev
    Next
    INDEX
    Explanations

    questions related to intentions and actions

    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
     ciudadana
    -0.33
    :\/\/
    -0.32
     samym
    -0.31
     consistent
    -0.31
     całym
    -0.30
     ciudadanía
    -0.30
     itself
    -0.29
     complete
    -0.29
     comerciais
    -0.29
     póź
    -0.29
    POSITIVE LOGITS
     blah
    1.06
     XYZ
    0.85
    blah
    0.83
     xyz
    0.77
     насељу
    0.73
    นู
    0.73
    〇〇
    0.71
    Blah
    0.70
    énario
    0.69
    ○○
    0.69
    Activations Density 0.228%

    No Known Activations