© 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
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 740
    Prev
    Next
    INDEX
    Explanations

    structured code elements, particularly declarations and definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ainfi
    -0.74
    üyor
    -0.73
     vectorielle
    -0.72
     abstrato
    -0.71
    adaptiveStyles
    -0.71
    QMetaType
    -0.64
     penghar
    -0.63
     ddelweddau
    -0.63
     المعيارى
    -0.62
     citoy
    -0.61
    POSITIVE LOGITS
     Petrov
    0.35
     McG
    0.34
     ravioli
    0.34
     Kowalski
    0.34
     PR
    0.34
    ita
    0.34
    mol
    0.33
    つ
    0.33
     correctly
    0.33
    SYNOPSIS
    0.33
    Activations Density 0.836%

    No Known Activations