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. 12264
    Prev
    Next
    INDEX
    Explanations

    references to physical structures and materials, particularly in the context of paths and trails

    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
     EconPapers
    -0.57
     AssemblyTitle
    -0.51
     aplicable
    -0.48
    ufficient
    -0.47
     Gerechtigkeit
    -0.45
    ableness
    -0.44
    قایناق‌لار
    -0.44
    HomeAsUpEnabled
    -0.44
    verifyException
    -0.44
    cestor
    -0.43
    POSITIVE LOGITS
     Administrativna
    0.42
     mouse
    0.41
    Mime
    0.39
    pptx
    0.39
     XML
    0.38
     MySql
    0.38
     miser
    0.38
     mail
    0.38
     PDF
    0.37
     beard
    0.37
    Activations Density 1.773%

    No Known Activations