© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 6775
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "friendly" and related sentiments 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 @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.87
    <h5>
    -0.78
    subplots
    -0.78
     NSCoder
    -0.76
     maș
    -0.73
    lanzen
    -0.71
     doInBackground
    -0.71
     uVar
    -0.71
     JComboBox
    -0.68
    ;#
    -0.67
    POSITIVE LOGITS
     friendly
    1.75
     Friendly
    1.61
    Friendly
    1.55
    friendly
    1.45
     friendliness
    1.25
     unfriendly
    1.25
     freundlich
    1.15
     vriende
    1.13
     pleasant
    1.08
     freund
    1.07
    Activations Density 0.065%

    No Known Activations