© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 11002
    Prev
    Next
    INDEX
    Explanations

    keywords and identifiers related to mapping and logging in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pri
    -0.59
     val
    -0.58
     ben
    -0.57
     المعيارى
    -0.57
     &
    -0.57
     Cha
    -0.57
     Link
    -0.56
     E
    -0.56
     Ter
    -0.56
     Cor
    -0.56
    POSITIVE LOGITS
    NUMX
    1.22
     Theſe
    1.17
     myſelf
    1.11
     pleaſure
    1.05
     Cæsar
    1.04
     itſelf
    1.02
     Monfieur
    1.02
     houſe
    1.01
     reaſon
    1.00
     purpoſe
    0.99
    Activations Density 0.743%

    No Known Activations