© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3662
    Prev
    Next
    INDEX
    Explanations

    scientific terminology and references related to biological processes and experimental outcomes

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

    technical numerical values and measurements, particularly in scientific or medical contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    ItemBackground
    -0.47
    הערות
    -0.44
    ErrorListener
    -0.42
     intptr
    -0.42
     Administrativna
    -0.41
    haikusbot
    -0.40
    msgTypes
    -0.39
    Дереккөздер
    -0.39
    PerformLayout
    -0.39
    staff
    -0.38
    POSITIVE LOGITS
     getItemId
    0.48
     decât
    0.48
     <>",
    0.47
     للمعارف
    0.45
    NewUrlParser
    0.43
     &___
    0.42
     EconPapers
    0.42
     tampoco
    0.41
    haviour
    0.40
    appartamento
    0.40
    Activations Density 0.633%

    No Known Activations