© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5476
    Prev
    Next
    INDEX
    Explanations

    phrases that imply enabling or facilitating actions 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 @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     desplaz
    -0.42
     Auseinander
    -0.36
     Behör
    -0.36
     Administrativna
    -0.36
     zufolge
    -0.34
     inscrição
    -0.34
     Sünde
    -0.34
     Aufenthal
    -0.33
     erfaren
    -0.33
     Folge
    -0.31
    POSITIVE LOGITS
     allowing
    1.65
     Allowing
    1.46
    allowing
    1.42
     permitting
    1.34
     enabling
    1.31
     letting
    1.24
     Enabling
    1.19
    Enabling
    1.16
     Letting
    1.14
     ensuring
    1.08
    Activations Density 0.223%

    No Known Activations