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
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 974
    Prev
    Next
    INDEX
    Explanations

    concepts and actions related to spirituality and internal contemplation

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

    followed by adverbs or auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    metaphorical becoming more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dışında
    -0.35
    forChild
    -0.32
     upraw
    -0.29
     gehouden
    -0.27
     ***!
    -0.26
     override
    -0.26
    override
    -0.26
     przyczyn
    -0.26
     zurückge
    -0.25
     salvajes
    -0.25
    POSITIVE LOGITS
    AddTagHelper
    0.76
     AssemblyCulture
    0.74
     metaphorical
    0.68
    AndEndTag
    0.68
    Personendaten
    0.64
    jsonwebtoken
    0.63
     betweenstory
    0.62
     ujednoznacz
    0.61
     /\.(
    0.61
    ettür
    0.60
    Activations Density 0.348%

    No Known Activations