© 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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 5403
    Prev
    Next
    INDEX
    Explanations

    references to education and professional accomplishments

    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
     Spokane
    -0.71
     OREGON
    -0.69
     Seattle
    -0.68
     Oregon
    -0.67
    Oregon
    -0.65
    seattle
    -0.65
     Puget
    -0.64
     Idaho
    -0.60
    Seattle
    -0.59
    IndentedString
    -0.56
    POSITIVE LOGITS
     Guyana
    1.22
     Barbados
    1.19
    Guyana
    1.14
     Jamaica
    1.11
     Trinidad
    1.09
     Tobago
    1.06
     Caribbean
    1.05
    Barbados
    1.04
    Trinidad
    1.04
    Jamaica
    1.04
    Activations Density 0.154%

    No Known Activations