Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3063
    Prev
    Next
    INDEX
    Explanations

    emotional expressions related to caregiving and childhood experiences

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

    Following "little," especially describing children

    np_acts-logits-general · gemini-2.0-flash

    little followed by young beings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſtand
    -0.87
     myſelf
    -0.86
     Efq
    -0.86
     uſed
    -0.83
     raiſ
    -0.83
     stepmother
    -0.81
     ſever
    -0.80
    AnchorStyles
    -0.80
     pleaſure
    -0.80
     ſta
    -0.76
    POSITIVE LOGITS
     little
    1.40
    little
    1.20
     LITTLE
    0.96
    Little
    0.96
     baby
    0.94
     Little
    0.93
     lil
    0.92
    LITTLE
    0.84
     precious
    0.81
    baby
    0.79
    Activations Density 0.096%

    No Known Activations