© 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. 1-GEMMASCOPE-RES-16K
    6. 9012
    Prev
    Next
    INDEX
    Explanations

    terms related to realization and concepts of conceptual understanding or achievement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.52
    esgue
    -0.52
     Duty
    -0.48
     univ
    -0.47
    estacks
    -0.47
     Surveillance
    -0.45
     Gustave
    -0.45
     PROP
    -0.43
    ẵn
    -0.43
    neſs
    -0.43
    POSITIVE LOGITS
     realisation
    1.70
     realization
    1.70
     realise
    1.40
     realising
    1.39
     realised
    1.39
     realizing
    1.35
     realises
    1.35
     realiz
    1.35
     realized
    1.34
     realize
    1.34
    Activations Density 0.351%

    No Known Activations