© 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. 5-GEMMASCOPE-RES-16K
    6. 829
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols related to formulas and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.89
     beginnetje
    -0.82
    Jeografia
    -0.76
     disambiguazione
    -0.75
     CreateTagHelper
    -0.75
    principalTable
    -0.70
    fjspx
    -0.70
     AssemblyProduct
    -0.69
     насељу
    -0.67
    SourceChecksum
    -0.67
    POSITIVE LOGITS
    endpush
    0.50
    TextWatcher
    0.46
     πρά
    0.43
    nicki
    0.42
     εγ
    0.42
     getrennt
    0.41
    べて
    0.40
    卡通
    0.40
    агности
    0.39
    hofen
    0.39
    Activations Density 1.047%

    No Known Activations