© 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. 30-GEMMASCOPE-RES-16K
    11. 10961
    Prev
    Next
    INDEX
    Explanations

    phrases related to improvement and positive outcomes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes before words related to improvement or positive qualities

    np_acts-logits-general · gemini-2.0-flash

    improving quality and performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.36
    ɵ
    -0.36
    woff
    -0.34
    +:+
    -0.33
    isContained
    -0.32
     Vande
    -0.30
    ocate
    -0.30
    adj
    -0.30
    eamento
    -0.30
    acebook
    -0.29
    POSITIVE LOGITS
     productivity
    1.20
     efficiency
    1.13
     readability
    1.11
     accuracy
    1.09
     quality
    1.05
     morale
    1.04
     reliability
    1.02
     credibility
    1.02
     integrity
    1.00
     performance
    0.99
    Activations Density 1.306%

    No Known Activations