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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 3027
    Prev
    Next
    INDEX
    Explanations

    the appearance of the speaker's perspective and opinions

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

    "I" followed by specific verbs or adverbs

    np_acts-logits-general · gemini-2.0-flash

    I don't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entanto
    -0.83
     however
    -0.80
    甚至
    -0.72
     jopa
    -0.71
    however
    -0.67
     sogar
    -0.65
     dokonce
    -0.63
     hatta
    -0.62
     bahkan
    -0.60
     thậm
    -0.59
    POSITIVE LOGITS
     przecież
    1.10
     Schließlich
    0.93
    畢竟
    0.93
     already
    0.92
    毕竟
    0.91
     ohnehin
    0.88
    already
    0.86
    Хьажоргаш
    0.84
     vốn
    0.81
     이미
    0.81
    Activations Density 0.682%

    No Known Activations