Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12917
    Prev
    Next
    INDEX
    Explanations

    references to public health initiatives and their implications for community support

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

    before nouns or adjectives

    np_acts-logits-general · gemini-2.0-flash

    German modal verbs and consequences

    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
     onboarding
    -1.10
     microbiome
    -1.09
     curated
    -0.95
     
    -0.93
     impactful
    -0.93
    COVID
    -0.91
     LGBTQ
    -0.90
    qPCR
    -0.90
     COVID
    -0.90
     Instagram
    -0.89
    POSITIVE LOGITS
     daß
    1.29
     läßt
    1.13
     muß
    1.09
     Daß
    1.06
    faßt
    1.05
     müßte
    0.94
     Einfluß
    0.93
     Bewußt
    0.92
     mußten
    0.90
     mußte
    0.90
    Activations Density 3.039%

    No Known Activations