© 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. 20-GEMMASCOPE-RES-131K
    6. 16390
    Prev
    Next
    INDEX
    Explanations

    terms related to absorption in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     kasarigan
    -0.68
    cienti
    -0.66
     ThemeData
    -0.60
    LookAnd
    -0.59
    createStatement
    -0.58
     Daniele
    -0.57
    ementara
    -0.57
    исправ
    -0.56
     propertyName
    -0.56
    writeFieldEnd
    -0.54
    POSITIVE LOGITS
    Absor
    0.77
     absorption
    0.77
     absorb
    0.74
     Absor
    0.71
     absorbs
    0.71
     Absorption
    0.68
     absorbed
    0.67
    Absorption
    0.66
     absorber
    0.66
    absorption
    0.65
    Activations Density 0.016%

    No Known Activations