© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5137
    Prev
    Next
    INDEX
    Explanations

    instances of the variable "v" with varying dimensions or iterations in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     feroit
    -0.55
    ParallelGroup
    -0.52
    BeginContext
    -0.50
     betweenstory
    -0.49
    hæ
    -0.48
     raiſ
    -0.47
     Suite
    -0.46
    TargetException
    -0.44
    TestCase
    -0.43
     发表于
    -0.43
    POSITIVE LOGITS
     v
    1.02
     V
    0.65
    V
    0.54
     étrangères
    0.48
     uv
    0.45
     scolaires
    0.45
    Atsauces
    0.44
    vv
    0.44
    Izvori
    0.42
     regalías
    0.41
    Activations Density 0.103%

    No Known Activations