© 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. 13-GEMMASCOPE-RES-16K
    6. 8197
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "emptiness" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessorType
    -0.51
     Inscrivez
    -0.48
    jbl
    -0.46
    LinkId
    -0.46
     inilah
    -0.45
     getOrder
    -0.45
    epoca
    -0.44
    cstdio
    -0.42
     Ngb
    -0.42
    relationship
    -0.41
    POSITIVE LOGITS
    Empty
    1.57
     Empty
    1.56
     empty
    1.55
    empty
    1.47
     EMPTY
    1.36
    EMPTY
    1.35
     emptiness
    1.23
    isEmpty
    1.20
     emptied
    1.18
    mpty
    1.16
    Activations Density 0.229%

    No Known Activations