© 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. 82855
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and interaction with a dialogue system

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

    robot answers or replies

    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
     Verhältnisse
    -0.26
     CanadaChoose
    -0.24
     formerly
    -0.24
     individual
    -0.23
     individually
    -0.22
    かつて
    -0.22
     rhestr
    -0.21
     surla
    -0.21
     sacrificing
    -0.21
    吁
    -0.21
    POSITIVE LOGITS
     betweenstory
    0.72
     queſta
    0.66
    AndEndTag
    0.64
     replies
    0.62
     AppCompatTheme
    0.60
    transQ
    0.59
     Anſ
    0.59
     linkovi
    0.59
     reply
    0.58
     Responses
    0.58
    Activations Density 0.137%

    No Known Activations