© 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-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 11883
    Prev
    Next
    INDEX
    Explanations

    nouns and phrases related to identity and social characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.76
    WriteTagHelper
    -0.73
     ſta
    -0.71
     ***!
    -0.66
     ſte
    -0.66
     snippetHide
    -0.65
     pleaſure
    -0.64
     تضيفلها
    -0.63
    twimg
    -0.63
    enumii
    -0.61
    POSITIVE LOGITS
    reszcie
    0.35
     sesi
    0.28
    สง
    0.28
    Hrsg
    0.28
     is
    0.28
     akhirnya
    0.28
     sik
    0.27
    "/",
    0.27
     sak
    0.26
     "*"
    0.26
    Activations Density 0.848%

    No Known Activations