© 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. 9-GEMMASCOPE-RES-16K
    11. 1161
    Prev
    Next
    INDEX
    Explanations

    references to machinery and machine learning concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portail
    -1.05
    endsection
    -1.04
     feroit
    -1.03
     polaire
    -1.00
    fjspx
    -0.98
     ainfi
    -0.94
     avoient
    -0.94
     larmes
    -0.93
     EnglishChoose
    -0.93
     Romains
    -0.93
    POSITIVE LOGITS
     machines
    1.79
    Machines
    1.64
    machines
    1.62
     machine
    1.61
     Machines
    1.59
     Machine
    1.49
    machine
    1.43
     MACHINE
    1.34
    Machine
    1.33
    MACHINE
    1.27
    Activations Density 0.061%

    No Known Activations