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. 1385
    Prev
    Next
    INDEX
    Explanations

    phrases related to government programs and initiatives

    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
    orianCalendar
    -0.55
    appliquent
    -0.53
    Vidite
    -0.52
    UnknownFields
    -0.49
    databind
    -0.49
     visualiser
    -0.49
    Viited
    -0.47
    Catégorie
    -0.47
    timeter
    -0.46
    mberto
    -0.46
    POSITIVE LOGITS
     program
    3.83
    program
    3.31
     Program
    3.27
    Program
    3.13
     PROGRAM
    2.96
     programme
    2.87
     programa
    2.76
     programs
    2.72
    PROGRAM
    2.64
     Programm
    2.52
    Activations Density 0.391%

    No Known Activations