© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 12705
    Prev
    Next
    INDEX
    Explanations

    geographic regions, particularly in the context of the United States

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SpringBootTest
    -0.40
    ReusableCell
    -0.40
     Bachchan
    -0.38
     headboard
    -0.38
     emis
    -0.38
     հղումներ
    -0.37
     Signalez
    -0.37
     Addon
    -0.37
    ]<<"
    -0.37
     --}}
    -0.36
    POSITIVE LOGITS
     Northeast
    1.48
     Northwest
    1.42
     Southwest
    1.39
    Northwest
    1.32
    Northeast
    1.31
     Southeast
    1.30
    Southwest
    1.27
     northeast
    1.20
     northwest
    1.14
     southwest
    1.13
    Activations Density 0.191%

    No Known Activations