© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10113
    Prev
    Next
    INDEX
    Explanations

    terms related to features and updates in a software context

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

    "Improved" or improvements

    np_acts-logits-general · gemini-2.0-flash

    change and improvement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 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
     EconPapers
    -0.69
     Italijanski
    -0.58
     незавершена
    -0.56
    fjspx
    -0.56
    󠁴
    -0.54
     doInBackground
    -0.53
    存于互联网档案馆
    -0.52
     invokingState
    -0.51
    常識
    -0.49
     himo
    -0.49
    POSITIVE LOGITS
     improvement
    0.45
     mejorando
    0.41
    改
    0.39
     improved
    0.38
     reform
    0.37
     improvements
    0.36
    improvement
    0.36
     progre
    0.36
     změ
    0.35
     cambiando
    0.35
    Activations Density 1.215%

    No Known Activations