© 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-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 7433
    Prev
    Next
    INDEX
    Explanations

    boolean values that indicate nullability or status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.61
     themſelves
    -0.55
     myſelf
    -0.55
     himſelf
    -0.54
     }:
    -0.53
    ApiOperation
    -0.53
    ppins
    -0.52
     Efq
    -0.52
    laş
    -0.52
     ſever
    -0.52
    POSITIVE LOGITS
     true
    4.01
    true
    3.72
     True
    3.52
    True
    3.52
     TRUE
    3.10
    TRUE
    2.81
     verdadero
    2.45
     vrai
    2.40
     verdadera
    2.35
     verdadeira
    2.26
    Activations Density 0.078%

    No Known Activations