© 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. 20-GEMMASCOPE-RES-131K
    11. 81907
    Prev
    Next
    INDEX
    Explanations

    abstract nouns describing qualities or states, particularly related to generality, stability, and distinctiveness

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

    abstract qualities like "ness" and "ity"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.53
     flesta
    -0.43
    multicolumn
    -0.42
     fleste
    -0.40
    PathVariable
    -0.38
     expend
    -0.38
    Selected
    -0.36
     egna
    -0.35
    mlx
    -0.35
    WriteLiteral
    -0.35
    POSITIVE LOGITS
    queness
    0.82
    yness
    0.81
    veness
    0.79
    lessness
    0.77
    ishness
    0.76
    uteness
    0.73
    mindedness
    0.72
    fulness
    0.71
    siveness
    0.71
     Simplicity
    0.71
    Activations Density 0.132%

    No Known Activations