© 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. 11-GEMMASCOPE-RES-16K
    11. 5141
    Prev
    Next
    INDEX
    Explanations

    text that refers to mechanisms or processes in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stones
    -0.82
    Попис
    -0.81
    RetentionPolicy
    -0.80
     ProtoMessage
    -0.76
     Sev
    -0.74
    Gord
    -0.72
    /***/
    -0.72
     héro
    -0.71
     Astoria
    -0.71
    phalt
    -0.71
    POSITIVE LOGITS
     mechanisms
    1.44
    Mechanisms
    1.44
     MECHAN
    1.42
     Mechanisms
    1.40
     mechanism
    1.36
     Mechanism
    1.33
    mechanism
    1.26
    mechan
    1.24
    Mechanism
    1.15
    MECHAN
    1.13
    Activations Density 0.096%

    No Known Activations