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. 21-GEMMASCOPE-RES-16K
    6. 14477
    Prev
    Next
    INDEX
    Explanations

    aspects related to numerical values and their implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.50
    EndContext
    -0.48
     tarif
    -0.44
     élevées
    -0.43
    حياتها
    -0.43
     démo
    -0.43
     tarifa
    -0.42
     elevada
    -0.41
    statistic
    -0.41
     econó
    -0.41
    POSITIVE LOGITS
    SharedDtor
    0.64
     ProtoMessage
    0.55
    AddTagHelper
    0.54
    ExecuteReader
    0.48
     InputDecoration
    0.48
    RectangleBorder
    0.46
    routeProvider
    0.44
     awakeFromNib
    0.44
     TextInputType
    0.43
    Tazama
    0.42
    Activations Density 1.486%

    No Known Activations