Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 21460
    Prev
    Next
    INDEX
    Explanations

    financial terminology and metrics related to the telecommunications industry

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

    telecom commission authorizes

    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
    PYX
    -0.50
     HAN
    -0.38
     XR
    -0.38
     gof
    -0.38
     XY
    -0.37
    chapters
    -0.37
     Jet
    -0.35
     hor
    -0.35
     COB
    -0.35
     PK
    -0.35
    POSITIVE LOGITS
     Normdatei
    0.56
     InputDecoration
    0.55
    lusconi
    0.52
    elemField
    0.50
     opérateurs
    0.49
     nonUne
    0.47
     regulador
    0.47
     telefónica
    0.47
     Superan
    0.46
     infrastruktur
    0.46
    Activations Density 0.011%

    No Known Activations