© 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. 14-GEMMASCOPE-RES-16K
    11. 7489
    Prev
    Next
    INDEX
    Explanations

    instances of the word "separate" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.40
     hoá
    -0.35
     veranderen
    -0.34
     Matériau
    -0.33
     unwilling
    -0.33
     <<<<<<<<<<<<<<
    -0.31
     changements
    -0.31
    ButterKnife
    -0.30
    richting
    -0.30
     hóa
    -0.30
    POSITIVE LOGITS
     separate
    1.52
    separate
    1.49
    Separate
    1.39
     Separate
    1.38
     seperate
    1.30
     separately
    1.27
     SEPAR
    1.17
     terpisah
    1.12
     separado
    1.05
     samostat
    1.05
    Activations Density 0.308%

    No Known Activations