© 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. 15014
    Prev
    Next
    INDEX
    Explanations

    information about personal details related to individuals, such as their family, age, and career status

    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
     bezeichneter
    -0.50
    atimes
    -0.49
    articulo
    -0.47
    XmlAccessType
    -0.45
    ujudkan
    -0.43
    mmä
    -0.43
    minster
    -0.43
    ablecer
    -0.43
    istive
    -0.43
     aastal
    -0.42
    POSITIVE LOGITS
    rawDesc
    0.84
    tvguidetime
    0.77
     propOrder
    0.76
    ReusableCell
    0.76
    IsContent
    0.73
    ResumeLayout
    0.68
     MonoBehaviour
    0.65
    %)$
    0.65
     ProtoMessage
    0.64
    Personensuche
    0.63
    Activations Density 0.262%

    No Known Activations