© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 642
    Prev
    Next
    INDEX
    Explanations

    phrases related to improvement and positive development in performance

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

    positive change

    np_acts-logits-general · gemini-2.0-flash

    positive changes or movement forward

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.31
    XmlAccessType
    -0.30
     CreateTagHelper
    -0.29
     burbujas
    -0.29
    還能
    -0.28
    bundes
    -0.28
     gärna
    -0.28
    繼續
    -0.27
    VersionUID
    -0.27
    DatabaseError
    -0.26
    POSITIVE LOGITS
    improved
    0.63
     improved
    0.63
    改善
    0.60
    amélioration
    0.60
     rectified
    0.58
     improvement
    0.56
    Improved
    0.54
     turnaround
    0.54
     comeback
    0.54
     Improved
    0.54
    Activations Density 0.372%

    No Known Activations