© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 150
    Prev
    Next
    INDEX
    Explanations

    references to session management and properties in code

    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
     CreateTagHelper
    -0.87
     disambiguazione
    -0.76
    IsContent
    -0.66
    verwijspagina
    -0.66
    HasAnnotation
    -0.64
    msgTypes
    -0.63
    TargetException
    -0.62
    InputTagHelper
    -0.61
     AssemblyVersion
    -0.59
    ImageContext
    -0.59
    POSITIVE LOGITS
     longitudinal
    0.50
    _
    0.50
     Normal
    0.48
     Anterior
    0.48
    final
    0.47
     Final
    0.46
     Saxe
    0.46
    Actual
    0.46
    Final
    0.46
    Electron
    0.46
    Activations Density 0.083%

    No Known Activations