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. 12971
    Prev
    Next
    INDEX
    Explanations

    references to local eateries and dining options

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

    Follows adjectives such as "newest", "successful", "second"

    np_acts-logits-general · gemini-2.0-flash

    newest, successful, second establishments

    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
     müßte
    -0.65
    ResourceManager
    -0.63
    ítmény
    -0.57
    ogna
    -0.57
    クタイ
    -0.56
     Accu
    -0.55
     simulated
    -0.55
     egli
    -0.53
     seno
    -0.53
    iomanip
    -0.52
    POSITIVE LOGITS
     hipster
    1.05
     indie
    0.95
     cowork
    0.95
     creatives
    0.88
     curated
    0.87
     Instagram
    0.82
     instagram
    0.82
    indie
    0.79
     queer
    0.78
     artisanal
    0.77
    Activations Density 0.312%

    No Known Activations