© 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. 10882
    Prev
    Next
    INDEX
    Explanations

    concepts related to recursive processes and iterations in experimentation

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

    Repeating actions or steps in a process

    np_acts-logits-general · gemini-2.0-flash

    repeating processes and sequences

    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
    MemoryWarning
    -0.61
    Personensuche
    -0.57
    bership
    -0.53
     سكانية
    -0.53
    AddTagHelper
    -0.53
     NSCoder
    -0.52
     StatefulWidget
    -0.50
    tonsoft
    -0.47
    PerformLayout
    -0.46
    μβρίου
    -0.45
    POSITIVE LOGITS
     repeat
    2.84
     Repeat
    2.50
     repeating
    2.50
     repeats
    2.48
    Repeat
    2.47
    repeat
    2.45
     repeated
    2.23
     repetition
    2.16
     repetir
    2.09
    repe
    2.05
    Activations Density 0.527%

    No Known Activations