© 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-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 10006
    Prev
    Next
    INDEX
    Explanations

    terms related to infinity and the concept of infinite properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    timbangkan
    -0.36
    ciphertext
    -0.35
    さぎ
    -0.35
    RequestContext
    -0.35
     epist
    -0.34
    WebpackPlugin
    -0.33
     Epist
    -0.33
     équipe
    -0.33
     Logical
    -0.33
     chart
    -0.32
    POSITIVE LOGITS
     INFIN
    0.77
     infinitely
    0.73
     Infinite
    0.71
    INFIN
    0.71
     infinit
    0.71
    infinite
    0.69
     infinite
    0.69
    Infinity
    0.69
    Personensuche
    0.68
     infinity
    0.67
    Activations Density 0.238%

    No Known Activations