© 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. 33-GEMMASCOPE-RES-16K
    11. 7578
    Prev
    Next
    INDEX
    Explanations

    metadata related to the creation and modification of files

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EDEFAULT
    -0.34
    Already
    -0.32
    already
    -0.32
    әрмәләр
    -0.31
     initComponents
    -0.31
    Existing
    -0.30
     pouvoit
    -0.30
     already
    -0.30
     Weeks
    -0.30
     Already
    -0.29
    POSITIVE LOGITS
     last
    1.19
     created
    1.09
     modified
    1.08
     updated
    1.07
     Created
    1.00
     updatedAt
    0.98
    LastModified
    0.97
    Created
    0.96
     Modified
    0.96
     modification
    0.95
    Activations Density 0.379%

    No Known Activations