© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5437
    Prev
    Next
    INDEX
    Explanations

    coding-related terms or identifiers

    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
    tvguidetime
    -0.65
     leſs
    -0.63
    !*\
    -0.58
     Administrativna
    -0.58
     betweenstory
    -0.57
     raiſ
    -0.57
    UnknownFieldSet
    -0.55
    ፩
    -0.55
     ſeveral
    -0.54
    rungsseite
    -0.53
    POSITIVE LOGITS
    d
    2.80
     d
    1.90
    D
    1.45
     D
    1.27
    d
    1.23
    getD
    1.22
    д
    1.05
     д
    0.96
    د
    0.96
    ᴅ
    0.94
    Activations Density 0.314%

    No Known Activations