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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 4151
    Prev
    Next
    INDEX
    Explanations

    geographical locations and notable events associated with them

    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
     Baloch
    -0.63
     Worcestershire
    -0.59
     Umb
    -0.58
     Wic
    -0.58
     Jiang
    -0.56
     Quin
    -0.55
     Sault
    -0.55
     Luanda
    -0.55
    onAttach
    -0.54
     Macau
    -0.54
    POSITIVE LOGITS
     Tennessee
    1.70
     Nashville
    1.59
    Tennessee
    1.51
     Tenn
    1.45
    Nashville
    1.39
     TN
    1.32
     Knoxville
    1.29
     Memphis
    1.29
     Chattanooga
    1.16
    Memphis
    1.15
    Activations Density 0.207%

    No Known Activations