© 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. 3-GEMMASCOPE-RES-16K
    11. 5919
    Prev
    Next
    INDEX
    Explanations

    occurrences of the preposition "on."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     мәкал
    -0.57
     informée
    -0.48
    səhifə
    -0.47
    AddTagHelper
    -0.47
    rentina
    -0.46
    skjaer
    -0.46
    haikusbot
    -0.45
     للاسماء
    -0.45
    stupid
    -0.45
    iſten
    -0.45
    POSITIVE LOGITS
    PerformLayout
    0.50
    Географиясе
    0.47
    __':
    0.40
    ]+=
    0.38
     Kirchen
    0.37
    rangle
    0.35
    LayoutManager
    0.35
    SequentialGroup
    0.35
    сятся
    0.34
    AddWithValue
    0.34
    Activations Density 0.036%

    No Known Activations