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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1388
    Prev
    Next
    INDEX
    Explanations

    terminology related to proteins and their biological contexts

    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
     muß
    -1.39
     läßt
    -1.38
     daß
    -1.33
     idéia
    -1.32
     müßte
    -1.23
     Moslem
    -1.13
     mußte
    -1.08
     Daß
    -1.08
     mußten
    -1.04
    faßt
    -0.98
    POSITIVE LOGITS
     microbiome
    1.26
     impactful
    1.19
     onboarding
    1.16
    TLDR
    1.15
     curated
    1.14
     incentiv
    1.09
     LGBTQ
    1.05
     immersive
    1.01
     nuanced
    1.00
     foundational
    0.99
    Activations Density 9.432%

    No Known Activations