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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 1370
    Prev
    Next
    INDEX
    Explanations

    terms related to timepieces and their characteristics

    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
    Geplaatst
    -0.99
     AssemblyCulture
    -0.91
    InjectAttribute
    -0.88
    EDEFAULT
    -0.87
    principalColumn
    -0.86
    IonicModule
    -0.85
    tagHelperRunner
    -0.85
    EndContext
    -0.84
    sizeCache
    -0.84
    StructEnd
    -0.84
    POSITIVE LOGITS
    -
    0.58
     data
    0.52
    的所有
    0.51
    opsida
    0.51
     services
    0.51
    úgó
    0.47
     service
    0.47
     đa
    0.45
    gav
    0.44
     banyak
    0.41
    Activations Density 6.934%

    No Known Activations