© 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. 80461
    Prev
    Next
    INDEX
    Explanations

    technical terms and parameter definitions related to electronic circuits and systems

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

    industrial electronic systems

    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
    twimg
    -0.72
     Chwiliwch
    -0.58
    ۝
    -0.47
    ukone
    -0.46
    DECREF
    -0.46
    ็จ
    -0.45
    MarshalTo
    -0.45
    JSONException
    -0.44
    edoc
    -0.44
    ̈́
    -0.43
    POSITIVE LOGITS
     industriales
    0.49
     industriels
    0.47
     Anwendungen
    0.47
     Geräte
    0.46
     industriel
    0.45
     cihaz
    0.44
     cérami
    0.43
     industrielle
    0.43
     Öffnungszeiten
    0.43
     commerciales
    0.43
    Activations Density 0.601%

    No Known Activations