© 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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 10129
    Prev
    Next
    INDEX
    Explanations

    concepts related to human uniqueness and the challenges of existence, particularly in the context of childbirth and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.55
    utilisons
    -0.55
    脚注の使い方
    -0.54
    Hochspringen
    -0.53
    
    -0.52
     createContext
    -0.51
    hydrates
    -0.49
    impre
    -0.48
    atoon
    -0.47
    Hentet
    -0.46
    POSITIVE LOGITS
     necessariamente
    0.64
    styleable
    0.62
    bootstrapcdn
    0.58
    protoimpl
    0.57
    }\]
    0.56
     necesariamente
    0.54
     nécessairement
    0.54
    TemporalType
    0.53
     mergeFrom
    0.51
    Jereo
    0.50
    Activations Density 0.383%

    No Known Activations