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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 1030
    Prev
    Next
    INDEX
    Explanations

    expressions related to methods or ways of doing things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "way" or "ways"

    np_acts-logits-general · gemini-2.0-flash

    method or manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     elástica
    -0.34
    pecabezas
    -0.32
     lunak
    -0.32
    NullException
    -0.32
     couronne
    -0.31
     Berufs
    -0.31
     dormitórios
    -0.30
     singen
    -0.30
     orçamento
    -0.30
     cerah
    -0.30
    POSITIVE LOGITS
     way
    1.15
     WAY
    1.10
     Way
    1.05
     Ways
    1.05
    Way
    1.02
    Ways
    0.99
     ways
    0.98
     WAYS
    0.93
    way
    0.87
    GenerationType
    0.81
    Activations Density 0.185%

    No Known Activations