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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 1390
    Prev
    Next
    INDEX
    Explanations

    technical terms and statistical measures relating to experimental design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ybė
    -0.30
    Geplaatst
    -0.30
     HES
    -0.28
    ADORES
    -0.28
    鹅
    -0.27
     Económica
    -0.27
    ➟
    -0.27
    nées
    -0.27
    ERT
    -0.27
    鵝
    -0.26
    POSITIVE LOGITS
     CI
    1.73
     MI
    1.61
     JI
    1.57
     SI
    1.57
    CI
    1.55
     EI
    1.55
     PI
    1.53
     FI
    1.52
     KI
    1.51
     YI
    1.51
    Activations Density 1.643%

    No Known Activations