© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 84118
    Prev
    Next
    INDEX
    Explanations

    instances of the keyword "public" in a programming context

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

    public code elements

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    CppMethod
    -0.84
    Према
    -0.79
    fjspx
    -0.78
     CURIAM
    -0.76
     resourceCulture
    -0.76
     pleaſure
    -0.75
     autorytatywna
    -0.75
    bootstrapcdn
    -0.74
     HasFactory
    -0.71
    хьтан
    -0.70
    POSITIVE LOGITS
     přes
    0.28
     extracción
    0.27
     do
    0.27
    randrange
    0.26
     Vorsch
    0.26
     tekem
    0.25
     sp
    0.23
    </td>
    0.23
     inoxidable
    0.23
     stej
    0.23
    Activations Density 0.002%

    No Known Activations