Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 6055
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations related to calculus and differential equations

    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
     piele
    -0.56
     esimer
    -0.52
     Genehmigung
    -0.52
     punggung
    -0.50
     picioare
    -0.49
     lisäksi
    -0.48
    NameInMap
    -0.46
     tertinggi
    -0.46
     Mehrheit
    -0.44
     Bewußt
    -0.43
    POSITIVE LOGITS
    Delta
    3.27
     Delta
    3.06
     delta
    2.45
     DELTA
    2.28
     Δ
    2.20
    DELTA
    2.19
    Δ
    2.14
    ∆
    1.68
     ∆
    1.66
    delta
    1.62
    Activations Density 0.154%

    No Known Activations