© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 126382
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific measurements and outcomes

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

    plural nouns ending in s

    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
    WaitGroup
    -0.68
    Datuak
    -0.60
     RSSSF
    -0.56
     CGSize
    -0.54
    istoitu
    -0.53
    balleur
    -0.50
     StringTokenizer
    -0.50
     Мексичка
    -0.50
    Jer
    -0.48
     rhestr
    -0.47
    POSITIVE LOGITS
    stā
    0.40
    LikeLiked
    0.40
    wikkeld
    0.39
    ⓧ
    0.39
    uxxxx
    0.37
     experiences
    0.36
     mergeFrom
    0.36
    ("}\
    0.35
     complexities
    0.35
     conductas
    0.34
    Activations Density 0.233%

    No Known Activations