© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15963
    Prev
    Next
    INDEX
    Explanations

    references to legal roles, positions, and their associated responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    MethodManager
    -0.54
     hydrauli
    -0.51
    BufferException
    -0.48
    wpi
    -0.47
    NgModule
    -0.46
    ymas
    -0.45
    uilla
    -0.44
    MessageDigest
    -0.44
     CommonModule
    -0.43
     jaundice
    -0.43
    POSITIVE LOGITS
     position
    2.68
     positions
    2.53
     Position
    2.28
    position
    2.12
     Positions
    2.11
     POSITION
    2.07
    Position
    2.05
    positions
    1.99
    Positions
    1.86
     posisi
    1.86
    Activations Density 0.319%

    No Known Activations