© 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. 5-GEMMASCOPE-RES-16K
    11. 13774
    Prev
    Next
    INDEX
    Explanations

    references to research methodologies and study evaluations

    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
     nadzie
    -0.59
     negeri
    -0.59
    empêcher
    -0.58
    olfen
    -0.55
     espoir
    -0.55
     Metropolitana
    -0.54
     diisi
    -0.54
    occuper
    -0.53
     ayudarte
    -0.53
     garçons
    -0.52
    POSITIVE LOGITS
    HasAnnotation
    0.83
     DataTypes
    0.80
     onAnimation
    0.78
    Personensuche
    0.75
     विश्वसनीयता
    0.74
     WebDriverWait
    0.73
    InjectAttribute
    0.73
    LLocation
    0.73
     how
    0.72
    SourceChecksum
    0.72
    Activations Density 0.575%

    No Known Activations