© 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. 0-GEMMASCOPE-RES-16K
    11. 8684
    Prev
    Next
    INDEX
    Explanations

    terms related to deletion and data removal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Versorgung
    -0.49
     stră
    -0.46
     dessutom
    -0.45
     masiva
    -0.44
     menengah
    -0.44
     dále
    -0.42
     terjangkau
    -0.41
     regalías
    -0.40
     prostředí
    -0.40
    orElseThrow
    -0.40
    POSITIVE LOGITS
     deleted
    1.34
     deleting
    1.28
     deletes
    1.27
     delete
    1.25
     deletion
    1.23
     Delete
    1.18
    Deleted
    1.13
     Deletion
    1.12
     Deleted
    1.12
     Deletes
    1.08
    Activations Density 0.155%

    No Known Activations