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. 16-GEMMASCOPE-RES-16K
    6. 12623
    Prev
    Next
    INDEX
    Explanations

    titles and themes related to existentialism and emotional depth in literary works

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

    Titles of works, including books and songs

    np_acts-logits-general · gemini-2.0-flash

    titles of works and projects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ynchronously
    -0.58
    っとり
    -0.57
    سمبر
    -0.57
     חיצוניים
    -0.56
    setVerticalGroup
    -0.54
     déterminé
    -0.54
    seamnă
    -0.53
    볍
    -0.53
    힣
    -0.52
     efectivamente
    -0.51
    POSITIVE LOGITS
    ſelves
    0.77
     Majefty
    0.74
    ſelf
    0.71
    +#+
    0.66
    matchCondition
    0.64
     Inſ
    0.63
    AndEndTag
    0.63
    SOUNDBITE
    0.63
     Houſe
    0.63
    SuppressLint
    0.61
    Activations Density 0.410%

    No Known Activations