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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 14455
    Prev
    Next
    INDEX
    Explanations

    terms related to mechanical systems and their functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    posedge
    -0.57
    +#+#
    -0.54
     <<<<<<<<<<<<<<
    -0.52
    transQ
    -0.51
    Personendaten
    -0.50
     AssemblyProduct
    -0.49
    coque
    -0.49
    StructEnd
    -0.46
    出版年
    -0.46
    MenuInflater
    -0.45
    POSITIVE LOGITS
     damping
    0.47
    damping
    0.43
     damp
    0.42
    damp
    0.42
     motion
    0.41
    chanical
    0.39
    Elite
    0.38
    motion
    0.37
     spring
    0.36
     patin
    0.36
    Activations Density 0.501%

    No Known Activations