© 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. 18-GEMMASCOPE-RES-16K
    11. 6406
    Prev
    Next
    INDEX
    Explanations

    descriptions of crowded environments and their contrasts, particularly related to food and dining experiences

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

    crowdedness or expectation

    np_acts-logits-general · gemini-2.0-flash

    crowded, full, busy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     domicili
    -0.53
    vors
    -0.48
     embarazo
    -0.45
    underland
    -0.45
    èvement
    -0.44
     대해
    -0.44
    atite
    -0.43
    PAIGN
    -0.43
     vĩnh
    -0.43
    ɨ
    -0.43
    POSITIVE LOGITS
     crowded
    1.71
     crowds
    1.49
     crowd
    1.43
     congested
    1.40
     overcrowded
    1.40
     busy
    1.39
     crowding
    1.37
     busiest
    1.36
     overcrowding
    1.34
    crow
    1.30
    Activations Density 0.135%

    No Known Activations