© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 11294
    Prev
    Next
    INDEX
    Explanations

    phrases related to perceptions and opinions about morality and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.57
     للاسماء
    -0.57
    Honours
    -0.51
     arşivlendi
    -0.49
    rungsseite
    -0.48
    fjspx
    -0.47
     utafitiHapana
    -0.47
     wireType
    -0.45
     <=",
    -0.45
    StoryboardSegue
    -0.45
    POSITIVE LOGITS
     نزد
    0.58
     بالنسبة
    0.56
     لدى
    0.46
    labus
    0.44
    occuper
    0.43
    makeText
    0.41
     uważ
    0.40
    ModelSerializer
    0.40
     apud
    0.40
     نظر
    0.37
    Activations Density 0.496%

    No Known Activations