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
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 4395
    Prev
    Next
    INDEX
    Explanations

    instances of the article "a."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.94
     EconPapers
    -0.84
    parsedMessage
    -0.84
     Chwiliwch
    -0.83
    出版年
    -0.78
     kasarigan
    -0.77
    httphttps
    -0.76
    évaluateur
    -0.75
    hoeddwyd
    -0.73
     ब्रेकडाउन
    -0.73
    POSITIVE LOGITS
     a
    0.62
     the
    0.52
    ↵
    0.44
     Make
    0.44
     my
    0.43
    Make
    0.43
     
    0.41
    Create
    0.39
     Find
    0.39
    Take
    0.38
    Activations Density 0.335%

    No Known Activations