© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 9161
    Prev
    Next
    INDEX
    Explanations

    terms related to genetic variation and research methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Academic/scientific writing describing a process

    np_acts-logits-general · gemini-2.0-flash

    genome analysis and simulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    faßt
    -1.09
     daß
    -1.03
     idéia
    -1.00
     muß
    -0.99
     definately
    -0.89
     läßt
    -0.87
     Einfluß
    -0.83
     biß
    -0.82
     Schluß
    -0.77
    Basically
    -0.74
    POSITIVE LOGITS
     incentiv
    1.00
     onboarding
    0.97
     microbiome
    0.95
     impactful
    0.93
     leveraging
    0.93
     nuanced
    0.91
     Notably
    0.86
     overarching
    0.84
     curated
    0.81
     foundational
    0.80
    Activations Density 4.516%

    No Known Activations