© 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. 2-GEMMASCOPE-RES-16K
    6. 13091
    Prev
    Next
    INDEX
    Explanations

    phrases indicating hierarchical or associative relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     faſt
    -0.91
     juſ
    -0.90
     ſta
    -0.88
     ſche
    -0.86
     pleaſure
    -0.85
     ſever
    -0.80
     ſtate
    -0.77
     purpoſe
    -0.77
     anſ
    -0.76
     ſtand
    -0.75
    POSITIVE LOGITS
     of
    2.14
     Of
    1.25
     OF
    1.15
    Of
    1.09
    of
    1.09
     của
    1.08
    ของ
    1.02
     של
    0.87
    オブ
    0.85
     ऑफ
    0.82
    Activations Density 1.582%

    No Known Activations