© 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. 70830
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal projects and technical inquiries

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

    I am doing something

    np_acts-logits-general · gemini-2.5-flash-lite

    instances of first-person self-reference (tokens signaling the author/user speaking about their own actions, state, or possessions).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     doInBackground
    -0.44
     urbanas
    -0.36
    initComponents
    -0.33
    WriteTagHelper
    -0.31
    Cyfarwyddwr
    -0.30
    <?
    -0.29
    abcdefghijklmnop
    -0.29
     cimetière
    -0.29
     Schauspielerin
    -0.28
     táctil
    -0.28
    POSITIVE LOGITS
     ब्रेकडाउन
    0.77
    
    0.63
    rungsseite
    0.63
    fusions
    0.62
     beginnetje
    0.59
     للمعارف
    0.59
     يتيمه
    0.58
    ſelben
    0.57
     fashiola
    0.55
    ंदीखरीदारी
    0.54
    Activations Density 0.091%

    No Known Activations