© 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. 21-GEMMASCOPE-RES-16K
    11. 10884
    Prev
    Next
    INDEX
    Explanations

    references to historical names and titles related to organizations and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Osorio
    -0.32
     Auer
    -0.30
     poursuivre
    -0.29
     Marín
    -0.29
     poursuite
    -0.28
     emel
    -0.28
     Ersatz
    -0.28
     spare
    -0.27
     MINOR
    -0.27
     l
    -0.27
    POSITIVE LOGITS
     restoring
    0.85
     restored
    0.85
     revival
    0.85
     restores
    0.82
     CreateTagHelper
    0.82
     revive
    0.81
     restoration
    0.78
     reviving
    0.78
     restore
    0.78
     الحره
    0.75
    Activations Density 0.385%

    No Known Activations