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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 6032
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terminology related to biochemistry and molecular biology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CIM
    -1.05
     RIM
    -1.01
     Jem
    -1.00
     CSM
    -0.99
     Vim
    -0.99
    Jem
    -0.98
     LAM
    -0.98
     SPM
    -0.96
     Cim
    -0.96
     PIM
    -0.96
    POSITIVE LOGITS
    principalTable
    0.73
     MCC
    0.50
     MW
    0.50
     MG
    0.50
     MSS
    0.50
     Sulawesi
    0.49
    τεύ
    0.45
     MF
    0.45
     MK
    0.44
     MB
    0.44
    Activations Density 4.767%

    No Known Activations