© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 95821
    Prev
    Next
    INDEX
    Explanations

    the term "superficial" in various contexts, often related to layers or levels of analysis

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

    superficial aspects

    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
     Wikimedijinoj
    -0.70
     queſta
    -0.68
    writeFieldEnd
    -0.67
    adaptiveStyles
    -0.66
     nakalista
    -0.65
     ſta
    -0.65
    UserScript
    -0.64
    MemoryWarning
    -0.64
    ustimmung
    -0.63
    rrggbb
    -0.62
    POSITIVE LOGITS
     superficial
    1.60
     superfic
    1.25
    ficial
    0.91
    表面
    0.90
     cursory
    0.87
     surface
    0.86
     поверх
    0.80
     Surface
    0.73
     SURFACE
    0.71
     superficie
    0.69
    Activations Density 0.031%

    No Known Activations