© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 14486
    Prev
    Next
    INDEX
    Explanations

    references to alpha and beta proteins involved in biochemical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
     /\.(
    -0.40
     ακόμα
    -0.38
     kuş
    -0.36
    躇
    -0.35
     inglesa
    -0.35
    ILayout
    -0.33
     gelingt
    -0.33
    ถ
    -0.32
     χρήση
    -0.32
    s
    -0.32
    POSITIVE LOGITS
     alpha
    2.27
     Alpha
    2.23
     Delta
    2.13
     beta
    2.11
     Beta
    2.08
     Gamma
    2.06
     gamma
    2.05
     Sigma
    2.02
     delta
    1.96
    Alpha
    1.95
    Activations Density 0.697%

    No Known Activations