© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 9732
    Prev
    Next
    INDEX
    Explanations

    terms related to the removal or disassembly of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ivelany
    -0.50
     ftate
    -0.40
    RequiresApi
    -0.40
    RenderAtEndOf
    -0.40
    WriteTagHelper
    -0.40
    뀐
    -0.36
    oneofs
    -0.35
    Brainz
    -0.35
    HasBeenSet
    -0.35
    modelBuilder
    -0.35
    POSITIVE LOGITS
     removed
    0.77
     REMOV
    0.75
     removal
    0.73
    removed
    0.73
     Removing
    0.73
     removing
    0.72
     remove
    0.69
     removable
    0.69
     Remove
    0.66
    Removing
    0.66
    Activations Density 0.559%

    No Known Activations