© 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. 17-GEMMASCOPE-RES-16K
    6. 7528
    Prev
    Next
    INDEX
    Explanations

    elements related to leadership roles and professional transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    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
    -1.36
     daß
    -1.33
     läßt
    -1.22
     idéia
    -1.19
     skall
    -1.18
     mußte
    -0.99
    faßt
    -0.99
     müßte
    -0.95
     Moslem
    -0.93
     Einfluß
    -0.91
    POSITIVE LOGITS
     onboarding
    1.19
     ⁠
    1.15
     impactful
    1.13
     incentiv
    1.07
     
    0.99
    . 
    0.96
     curated
    0.95
     prioriti
    0.95
    ⁠
    0.95
     aligns
    0.95
    Activations Density 1.424%

    No Known Activations