© 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. 10089
    Prev
    Next
    INDEX
    Explanations

    function definitions and method calls in code

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

    Code snippets with parentheses and brackets

    np_acts-logits-general · gemini-2.0-flash

    code structure and data manipulation

    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
    WebVitals
    -0.74
     autorytatywna
    -0.66
     CreateTagHelper
    -0.60
     kasarigan
    -0.60
    MemoryWarning
    -0.57
     beginnetje
    -0.57
    ClientSize
    -0.55
     ब्रेकडाउन
    -0.55
    GOTREF
    -0.55
     SDLK
    -0.55
    POSITIVE LOGITS
    sweise
    0.49
     interrump
    0.43
     detail
    0.40
     information
    0.40
     Giovan
    0.40
     combined
    0.39
     combining
    0.38
     equivalent
    0.37
     kombin
    0.37
    épaisseur
    0.37
    Activations Density 1.470%

    No Known Activations