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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1408
    Prev
    Next
    INDEX
    Explanations

    expressions related to feelings of longing or absence

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

    someone is absent

    np_acts-logits-general · gemini-2.0-flash

    absence and being away

    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
    ItemBackground
    -0.66
     nahilalakip
    -0.62
    GenerationType
    -0.55
    UserScript
    -0.54
     snippetHide
    -0.54
    subpackage
    -0.53
     ویکی‌پدی
    -0.52
    +#+
    -0.51
    softc
    -0.51
    slidesToShow
    -0.49
    POSITIVE LOGITS
     away
    1.78
     Away
    1.61
     absent
    1.56
     absence
    1.55
    Away
    1.49
     AWAY
    1.41
    absent
    1.38
    away
    1.37
    Absent
    1.33
     absences
    1.33
    Activations Density 0.241%

    No Known Activations