© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 104
    Prev
    Next
    INDEX
    Explanations

    phrases indicating direction or progression towards a conclusion or outcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Calvo
    -0.83
     riuscito
    -0.75
    5
    -0.73
     foglal
    -0.73
     grunn
    -0.69
     fatica
    -0.69
    T
    -0.68
     assoluto
    -0.68
     печа
    -0.67
     Integrity
    -0.66
    POSITIVE LOGITS
    toward
    1.83
    towards
    1.80
     toward
    1.77
     Towards
    1.76
     Toward
    1.74
    Towards
    1.73
     towards
    1.66
    Toward
    1.61
     hacia
    1.24
     TOW
    1.18
    Activations Density 0.065%

    No Known Activations