Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 8576
    Prev
    Next
    INDEX
    Explanations

    geographical locations and associated names or references

    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
     Bör
    -0.54
    PointerException
    -0.51
     Tsch
    -0.50
     London
    -0.49
     Tokyo
    -0.45
    東京
    -0.45
    London
    -0.44
    XmlSchema
    -0.43
     Berliner
    -0.43
     Paris
    -0.43
    POSITIVE LOGITS
     Worcester
    1.40
     Allentown
    1.39
     Knoxville
    1.39
     Peoria
    1.32
     Greensboro
    1.31
     Asheville
    1.29
     Rochester
    1.28
     Wilmington
    1.27
     Wichita
    1.25
     Ipswich
    1.25
    Activations Density 0.994%

    No Known Activations