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. 24-GEMMASCOPE-RES-16K
    6. 4182
    Prev
    Next
    INDEX
    Explanations

    programming-related constructs and structures

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

    Code or math with subscripts and indexing

    np_acts-logits-general · gemini-2.0-flash

    code and mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    ^(@)
    -1.12
    
    -1.11
    tershire
    -1.10
     $_(
    -1.09
     ་་
    -1.09
    
    -1.08
    往下閱讀
    -1.08
     $_"
    -1.08
    encils
    -1.08
    ſelben
    -1.08
    POSITIVE LOGITS
     wikipagina
    -0.32
     pérd
    -0.33
     técn
    -0.35
     stället
    -0.36
     varandra
    -0.37
     própri
    -0.38
     användas
    -0.39
     anún
    -0.39
     camiset
    -0.39
     dek
    -0.40
    Activations Density 34.857%

    No Known Activations