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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6864
    Prev
    Next
    INDEX
    Explanations

    concepts related to religious worship and spiritual practices

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

    hinduism/yoga

    np_acts-logits-general · gemini-2.0-flash

    spiritual and devotional themes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.52
    ">//
    -0.46
    ChildScrollView
    -0.45
     referenties
    -0.44
    aarrggbb
    -0.43
     שוליים
    -0.42
    FirstResponder
    -0.42
     للمعارف
    -0.42
    RemoveField
    -0.42
     Ops
    -0.41
    POSITIVE LOGITS
     autorytatywna
    0.48
    RTEE
    0.48
    iastes
    0.47
    parsedMessage
    0.45
    UnusedPrivate
    0.40
     enfans
    0.38
    BASEPATH
    0.37
     Audiodateien
    0.35
    นะนำ
    0.35
    kloped
    0.35
    Activations Density 0.309%

    No Known Activations