© 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. 22-GEMMASCOPE-RES-16K
    11. 13148
    Prev
    Next
    INDEX
    Explanations

    phrases that express personalization and customization based on individual tastes and requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    personal preferences or needs

    np_acts-logits-general · gemini-2.0-flash

    personal tastes and needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SerializedName
    -0.62
    IBOutlet
    -0.61
     betweenstory
    -0.61
    AccessorTable
    -0.59
    UnusedPrivate
    -0.58
     devriez
    -0.55
    tonsoft
    -0.53
     OnTrigger
    -0.49
    енча
    -0.49
    migrationBuilder
    -0.49
    POSITIVE LOGITS
     preferences
    1.70
     tastes
    1.63
     preference
    1.49
     needs
    1.37
     taste
    1.28
     Preferences
    1.27
    preferences
    1.26
     preferred
    1.26
    needs
    1.18
     Preference
    1.16
    Activations Density 0.362%

    No Known Activations