© 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. 21-GEMMASCOPE-RES-16K
    11. 8780
    Prev
    Next
    INDEX
    Explanations

    phrases related to individual preferences and adaptability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     devriez
    -0.63
    SerializedName
    -0.58
     poveznice
    -0.57
     astore
    -0.57
    contentPane
    -0.56
    Хьажоргаш
    -0.56
    tonsoft
    -0.56
    енча
    -0.56
    migrationBuilder
    -0.56
     Rela
    -0.55
    POSITIVE LOGITS
     preferences
    1.73
     tastes
    1.55
     preference
    1.51
     preferred
    1.35
    preferences
    1.32
     interests
    1.31
     Preferences
    1.29
     prefer
    1.21
     Preference
    1.20
     taste
    1.19
    Activations Density 0.276%

    No Known Activations