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. 17-GEMMASCOPE-RES-16K
    6. 12
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to variables and their functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_17/width_16k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.62
     المعيارى
    -0.58
    atorics
    -0.54
    RTEX
    -0.53
     resourceCulture
    -0.52
     chapels
    -0.51
    CloseOperation
    -0.49
    tanleria
    -0.48
    naments
    -0.47
     Wikiseite
    -0.47
    POSITIVE LOGITS
    GTCX
    0.59
    EndContext
    0.42
    JpaRepository
    0.38
    Tracce
    0.37
    Demografía
    0.36
     expl
    0.34
    جمعیت
    0.33
     viewHolder
    0.32
    ")))
    0.32
    不多
    0.32
    Activations Density 1.449%

    No Known Activations