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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3615
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and units in scientific data

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

    Units of time and memory

    np_acts-logits-general · gemini-2.0-flash

    units of measurement

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    原始内容存档于
    -0.58
    ParallelGroup
    -0.53
     مشين
    -0.51
    enumii
    -0.50
    webElementXpaths
    -0.49
     semelh
    -0.48
     repuesto
    -0.47
    DispatchToProps
    -0.45
    enumi
    -0.44
    期刊论文
    -0.44
    POSITIVE LOGITS
    Millis
    0.44
    GetBytes
    0.43
     rupees
    0.42
     days
    0.42
     inches
    0.42
     граду
    0.42
    thâu
    0.42
    getMinutes
    0.42
     celsius
    0.41
    
    0.41
    Activations Density 0.536%

    No Known Activations