© 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. 2-GEMMASCOPE-RES-16K
    6. 8918
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or thanks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DidLoad
    -0.56
    ểu
    -0.56
    tvguidetime
    -0.53
    abestanden
    -0.51
    PMailer
    -0.51
    Jîn
    -0.50
    IsContent
    -0.50
    FieldBuilder
    -0.49
     Alquiler
    -0.49
     Compound
    -0.48
    POSITIVE LOGITS
    rrggbb
    0.66
    FormatException
    0.57
     SwitchCompat
    0.52
    SerializeField
    0.51
    adaptiveStyles
    0.51
     OMITBAD
    0.50
     psycopg
    0.48
     farby
    0.48
    Injector
    0.48
     JButton
    0.48
    Activations Density 0.516%

    No Known Activations