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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 3011
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of reserves or conservation

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

    the word "reserve" in various contexts (currency, fields, military service, etc.).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.77
    httphttps
    -0.59
    Życiorys
    -0.57
    antMatchers
    -0.56
    rungsseite
    -0.55
     viewDidLoad
    -0.55
    addGroup
    -0.51
     bezeichneter
    -0.50
     ujednoznacz
    -0.50
     informée
    -0.50
    POSITIVE LOGITS
     reserve
    0.74
    Reserve
    0.73
     Reserve
    0.73
     Reservation
    0.67
    Reserv
    0.66
     Reserv
    0.64
     conservation
    0.63
     RESERVE
    0.62
    reserve
    0.62
     reserv
    0.62
    Activations Density 0.275%

    No Known Activations